Key Features:
* Full-text search across all documents
* Auto-generated global term index
* Breadcrumb navigation for easy exploration
* Integration of official Raku docs and community modules
The Raku Knowledge Base is open source (Artistic 2.0 license): https://github.com/zag/raku-knowledge-base
This project is built entirely using the Podlite markup language, showcasing its capabilities for creating documentation systems.
Podlite itself announce post: https://news.ycombinator.com/item?id=40141980
thank you"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Show HN: The Raku Knowledge Base powered by Podlite markup language(Open-Source)"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["base"],"value":"https://raku-knowledge-base.podlite.org/"}},"_tags":["story","author_zagap","story_41734472","show_hn"],"author":"zagap","created_at":"2024-10-03T20:10:53Z","created_at_i":1727986253,"num_comments":0,"objectID":"41734472","points":8,"story_id":41734472,"story_text":"Hi !\nI'm excited to share the Raku Knowledge Base v1.0, a comprehensive resource for the Raku programming language.
Key Features:
* Full-text search across all documents
* Auto-generated global term index
* Breadcrumb navigation for easy exploration
* Integration of official Raku docs and community modules
The Raku Knowledge Base is open source (Artistic 2.0 license): https://github.com/zag/raku-knowledge-base
This project is built entirely using the Podlite markup language, showcasing its capabilities for creating documentation systems.
Podlite itself announce post: https://news.ycombinator.com/item?id=40141980
thank you","title":"Show HN: The Raku Knowledge Base powered by Podlite markup language(Open-Source)","updated_at":"2024-10-09T04:53:10Z","url":"https://raku-knowledge-base.podlite.org/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"dcgudeman"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"U.S. Army Plans to Power Bases with Tiny Nuclear Reactors"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.wsj.com/politics/national-security/u-s-army-plans-to-power-bases-with-tiny-nuclear-reactors-c41c1383"}},"_tags":["story","author_dcgudeman","story_45587873"],"author":"dcgudeman","children":[45587894],"created_at":"2025-10-15T03:42:56Z","created_at_i":1760499776,"num_comments":1,"objectID":"45587873","points":6,"story_id":45587873,"title":"U.S. Army Plans to Power Bases with Tiny Nuclear Reactors","updated_at":"2026-03-05T22:52:52Z","url":"https://www.wsj.com/politics/national-security/u-s-army-plans-to-power-bases-with-tiny-nuclear-reactors-c41c1383"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nnx"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"A Shakeup Is Coming for the Nation-State: AI and drones may shift basis of power"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.thenewatlantis.com/publications/a-shakeup-is-coming-for-the-nation-state"}},"_tags":["story","author_nnx","story_47539965"],"author":"nnx","created_at":"2026-03-27T07:43:51Z","created_at_i":1774597431,"num_comments":0,"objectID":"47539965","points":5,"story_id":47539965,"title":"A Shakeup Is Coming for the Nation-State: AI and drones may shift basis of power","updated_at":"2026-03-27T18:48:09Z","url":"https://www.thenewatlantis.com/publications/a-shakeup-is-coming-for-the-nation-state"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"oladekola"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Dynamic Online Recall for You (DORY) helps you find anything you've seen before online using whatever you remember about it. DORY also builds a cognitive context graph to organize your work into auto-updating workflows and serve them to you in real time based on your browsing context. Early beta testers have found super useful onboarding and training use cases for this feature in particular.
Video: https://www.youtube.com/watch?v=kRWTVu77mMc\nWebsite: https://www.usedory.com/
A bit about me: I'm a previously non-technical founder. Taught myself how to code mostly from scratch using AI tools. The most useful prompt in my self directed learning has been "explain this to me like I'm a smart 12 year old". Yes, DORY is a nod to the movie Finding Dory!"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Dory \u2013 AI Knowledge Base Powered by Browser History"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/kqlade/dory-frontend"}},"_tags":["story","author_oladekola","story_43619021"],"author":"oladekola","children":[43619078,43623958,43623960],"created_at":"2025-04-08T06:53:00Z","created_at_i":1744095180,"num_comments":4,"objectID":"43619021","points":4,"story_id":43619021,"story_text":"Dynamic Online Recall for You (DORY) helps you find anything you've seen before online using whatever you remember about it. DORY also builds a cognitive context graph to organize your work into auto-updating workflows and serve them to you in real time based on your browsing context. Early beta testers have found super useful onboarding and training use cases for this feature in particular.
Video: https://www.youtube.com/watch?v=kRWTVu77mMc\nWebsite: https://www.usedory.com/
A bit about me: I'm a previously non-technical founder. Taught myself how to code mostly from scratch using AI tools. The most useful prompt in my self directed learning has been "explain this to me like I'm a smart 12 year old". Yes, DORY is a nod to the movie Finding Dory!","title":"Dory \u2013 AI Knowledge Base Powered by Browser History","updated_at":"2025-04-08T19:37:59Z","url":"https://github.com/kqlade/dory-frontend"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lsviana"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Show HN: I made a knowledge base powered by Google Docs"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.circulardocs.com/"}},"_tags":["story","author_lsviana","story_27036027","show_hn"],"author":"lsviana","children":[27036028,27036081],"created_at":"2021-05-04T10:40:46Z","created_at_i":1620124846,"num_comments":2,"objectID":"27036027","points":4,"story_id":27036027,"title":"Show HN: I made a knowledge base powered by Google Docs","updated_at":"2024-09-20T08:30:37Z","url":"https://www.circulardocs.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bookofjoe"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power, a Battery-Focused Power Company, Raises $1B"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.nytimes.com/2025/10/08/business/dealbook/base-power-fundraise-dell.html"}},"_tags":["story","author_bookofjoe","story_45520317"],"author":"bookofjoe","children":[45520326],"created_at":"2025-10-08T20:35:26Z","created_at_i":1759955726,"num_comments":1,"objectID":"45520317","points":3,"story_id":45520317,"title":"Base Power, a Battery-Focused Power Company, Raises $1B","updated_at":"2026-03-05T22:48:10Z","url":"https://www.nytimes.com/2025/10/08/business/dealbook/base-power-fundraise-dell.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Bender"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Air Force to Use Wyoming-Made Portable Nuclear Reactors to Power Bases"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://cowboystatedaily.com/2025/08/07/air-force-to-use-wyoming-made-portable-nuclear-reactors-to-power-bases/"}},"_tags":["story","author_Bender","story_44876469"],"author":"Bender","created_at":"2025-08-12T14:14:47Z","created_at_i":1755008087,"num_comments":0,"objectID":"44876469","points":3,"story_id":44876469,"title":"Air Force to Use Wyoming-Made Portable Nuclear Reactors to Power Bases","updated_at":"2026-03-05T22:34:04Z","url":"https://cowboystatedaily.com/2025/08/07/air-force-to-use-wyoming-made-portable-nuclear-reactors-to-power-bases/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ggoo"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Throw It in the Box: The Sega Master System II Power Base RGB"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://nicole.express/2021/adapteur-i-hardly-know-eur.html"}},"_tags":["story","author_ggoo","story_29020888"],"author":"ggoo","created_at":"2021-10-28T00:31:53Z","created_at_i":1635381113,"num_comments":0,"objectID":"29020888","points":3,"story_id":29020888,"title":"Throw It in the Box: The Sega Master System II Power Base RGB","updated_at":"2024-09-20T09:38:36Z","url":"https://nicole.express/2021/adapteur-i-hardly-know-eur.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"daveorzach"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power raised $1 billion in Series D funding at a $13 billion valuation and launched Base Core, a U.S.-built home battery made in Austin."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power raises another $1B"}},"_tags":["story","author_daveorzach","story_49161808","ask_hn"],"author":"daveorzach","children":[49161832],"created_at":"2026-08-03T21:39:59Z","created_at_i":1785793199,"num_comments":2,"objectID":"49161808","points":2,"story_id":49161808,"story_text":"Base Power raised $1 billion in Series D funding at a $13 billion valuation and launched Base Core, a U.S.-built home battery made in Austin.","title":"Base Power raises another $1B","updated_at":"2026-08-04T14:27:47Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"figbert"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power Company: Manufacturing the Capability Cannon"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.notboring.co/p/base-power-company-chapter-3"}},"_tags":["story","author_figbert","story_49302756"],"author":"figbert","created_at":"2026-08-14T18:28:29Z","created_at_i":1786732109,"num_comments":0,"objectID":"49302756","points":2,"story_id":49302756,"title":"Base Power Company: Manufacturing the Capability Cannon","updated_at":"2026-08-14T21:19:07Z","url":"https://www.notboring.co/p/base-power-company-chapter-3"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ChrisArchitect"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power raises $1B in Series C and opens Factory 1 in Austin"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.baseamerican.com/"}},"_tags":["story","author_ChrisArchitect","story_45660594"],"author":"ChrisArchitect","created_at":"2025-10-21T19:35:17Z","created_at_i":1761075317,"num_comments":0,"objectID":"45660594","points":2,"story_id":45660594,"title":"Base Power raises $1B in Series C and opens Factory 1 in Austin","updated_at":"2026-03-05T22:52:09Z","url":"https://www.baseamerican.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ChrisArchitect"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power Raises 1B Series C"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.baseamerican.com/"}},"_tags":["story","author_ChrisArchitect","story_45520506"],"author":"ChrisArchitect","created_at":"2025-10-08T20:50:51Z","created_at_i":1759956651,"num_comments":0,"objectID":"45520506","points":2,"story_id":45520506,"title":"Base Power Raises 1B Series C","updated_at":"2026-03-05T22:48:10Z","url":"https://www.baseamerican.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nop_slide"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power raises $1B to deploy home batteries everywhere"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://techcrunch.com/2025/10/08/base-power-raises-1b-to-deploy-home-batteries-everywhere/"}},"_tags":["story","author_nop_slide","story_45518796"],"author":"nop_slide","created_at":"2025-10-08T17:54:41Z","created_at_i":1759946081,"num_comments":0,"objectID":"45518796","points":2,"story_id":45518796,"title":"Base Power raises $1B to deploy home batteries everywhere","updated_at":"2026-03-05T22:48:01Z","url":"https://techcrunch.com/2025/10/08/base-power-raises-1b-to-deploy-home-batteries-everywhere/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"neom"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power raises $1B in latest financing round led by Addition"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.reuters.com/business/energy/base-power-raises-1-billion-latest-financing-round-led-by-addition-2025-10-08/"}},"_tags":["story","author_neom","story_45517435"],"author":"neom","created_at":"2025-10-08T15:46:05Z","created_at_i":1759938365,"num_comments":0,"objectID":"45517435","points":2,"story_id":45517435,"title":"Base Power raises $1B in latest financing round led by Addition","updated_at":"2026-03-05T22:47:56Z","url":"https://www.reuters.com/business/energy/base-power-raises-1-billion-latest-financing-round-led-by-addition-2025-10-08/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"pseudolus"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"The nuclear reactors that could power bases on the Moon"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.bbc.com/future/article/20240417-the-nuclear-reactors-that-could-power-moon-bases"}},"_tags":["story","author_pseudolus","story_40082724"],"author":"pseudolus","created_at":"2024-04-19T01:53:20Z","created_at_i":1713491600,"num_comments":0,"objectID":"40082724","points":2,"story_id":40082724,"title":"The nuclear reactors that could power bases on the Moon","updated_at":"2024-09-20T16:52:46Z","url":"https://www.bbc.com/future/article/20240417-the-nuclear-reactors-that-could-power-moon-bases"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yamrzou"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"French and Raven's Bases of Power"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://en.wikipedia.org/wiki/French_and_Raven%27s_bases_of_power"}},"_tags":["story","author_yamrzou","story_38665075"],"author":"yamrzou","created_at":"2023-12-16T15:49:40Z","created_at_i":1702741780,"num_comments":0,"objectID":"38665075","points":2,"story_id":38665075,"title":"French and Raven's Bases of Power","updated_at":"2024-09-20T15:54:36Z","url":"https://en.wikipedia.org/wiki/French_and_Raven%27s_bases_of_power"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mac_bateman"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Hello all, I always loved curating my 'knowledge base' catalog on desktop.\nDiscovering AI capabilities last year left me with no choice but to create... an AI-powered knowledge base. I like to think about it as Dropbox and ChatGPT combined. It can also transcribe your recordings. To build this I used FastAPI and AngularJS. I also use Langchain for dealing with with LLMs and Modal for deployment and scalability. Happy to hear if someone finds it usefull :)."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Show HN: Knowbase \u2013 personal knowledge base powered by ChatGPT"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.knowbase.ai/"}},"_tags":["story","author_mac_bateman","story_37912480","show_hn"],"author":"mac_bateman","created_at":"2023-10-17T09:27:11Z","created_at_i":1697534831,"num_comments":0,"objectID":"37912480","points":2,"story_id":37912480,"story_text":"Hello all, I always loved curating my 'knowledge base' catalog on desktop.\nDiscovering AI capabilities last year left me with no choice but to create... an AI-powered knowledge base. I like to think about it as Dropbox and ChatGPT combined. It can also transcribe your recordings. To build this I used FastAPI and AngularJS. I also use Langchain for dealing with with LLMs and Modal for deployment and scalability. Happy to hear if someone finds it usefull :).","title":"Show HN: Knowbase \u2013 personal knowledge base powered by ChatGPT","updated_at":"2024-09-20T15:21:06Z","url":"https://www.knowbase.ai/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yarapavan"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Base Power Company: Building the Modern Power Company of the Electric Era"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.notboring.co/p/base-power-company"}},"_tags":["story","author_yarapavan","story_40356302"],"author":"yarapavan","created_at":"2024-05-14T15:33:34Z","created_at_i":1715700814,"num_comments":0,"objectID":"40356302","points":1,"story_id":40356302,"title":"Base Power Company: Building the Modern Power Company of the Electric Era","updated_at":"2024-09-20T17:04:08Z","url":"https://www.notboring.co/p/base-power-company"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"timthorn"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"UK Government signs \u00a32.9M Moon base nuclear power deal with Rolls-Royce"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.bbc.co.uk/news/uk-england-derbyshire-64982477"}},"_tags":["story","author_timthorn","story_35196484"],"author":"timthorn","created_at":"2023-03-17T12:56:46Z","created_at_i":1679057806,"num_comments":0,"objectID":"35196484","points":1,"story_id":35196484,"title":"UK Government signs \u00a32.9M Moon base nuclear power deal with Rolls-Royce","updated_at":"2024-09-20T13:41:30Z","url":"https://www.bbc.co.uk/news/uk-england-derbyshire-64982477"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"scotch_drinker"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"French and Raven's Bases of Power"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://en.wikipedia.org/wiki/French_and_Raven%27s_bases_of_power"}},"_tags":["story","author_scotch_drinker","story_20742986"],"author":"scotch_drinker","created_at":"2019-08-20T00:49:00Z","created_at_i":1566262140,"num_comments":0,"objectID":"20742986","points":1,"story_id":20742986,"title":"French and Raven's Bases of Power","updated_at":"2024-09-20T04:47:03Z","url":"https://en.wikipedia.org/wiki/French_and_Raven%27s_bases_of_power"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ohiovr"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Take a frozen wafer of deuterium ice and compress it with diamond anvil cell to 771 GPA, then fire very focused laser beams to culminate in the middle between the walls of the cell with increasing power to initiate fusion.
Source of idea: red dwarf stars like Proxima Centauri have pressures of around 3500 GPA yet are big enough to sustain fusion. The fusion power is very small and already on a mass basis, fusion power in the sun is very very small. Fusion energy of course is very big. The fuel lasts a long time.
At any rate this might be able to give us an idea of the smallest possible star if it were made of pure deuterium."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Diamond Anvil Cell Heater?"}},"_tags":["story","author_ohiovr","story_32670590","ask_hn"],"author":"ohiovr","created_at":"2022-09-01T01:18:06Z","created_at_i":1661995086,"num_comments":0,"objectID":"32670590","points":1,"story_id":32670590,"story_text":"Take a frozen wafer of deuterium ice and compress it with diamond anvil cell to 771 GPA, then fire very focused laser beams to culminate in the middle between the walls of the cell with increasing power to initiate fusion.
Source of idea: red dwarf stars like Proxima Centauri have pressures of around 3500 GPA yet are big enough to sustain fusion. The fusion power is very small and already on a mass basis, fusion power in the sun is very very small. Fusion energy of course is very big. The fuel lasts a long time.
At any rate this might be able to give us an idea of the smallest possible star if it were made of pure deuterium.","title":"Ask HN: Diamond Anvil Cell Heater?","updated_at":"2024-09-20T11:56:22Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"foundval"},"title":{"matchLevel":"none","matchedWords":[],"value":"Merge, Don't Queue"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://inside.basepowercompany.com/p/merge-dont-queue"}},"_tags":["story","author_foundval","story_49169861"],"author":"foundval","created_at":"2026-08-04T14:55:04Z","created_at_i":1785855304,"num_comments":0,"objectID":"49169861","points":9,"story_id":49169861,"title":"Merge, Don't Queue","updated_at":"2026-08-05T15:28:52Z","url":"https://inside.basepowercompany.com/p/merge-dont-queue"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gilbitron"},"story_text":{"matchLevel":"none","matchedWords":[],"value":""},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Raneto: Markdown-powered knowledge base for Node.js"},"url":{"matchLevel":"none","matchedWords":[],"value":"http://raneto.com"}},"_tags":["story","author_gilbitron","story_7832991"],"author":"gilbitron","children":[7833293,7833385,7833416,7833702,7833942,7834076,7834103,7834198,7834226,7834828,7834966,7835050,7835086,7838338,7838347,7840978,7844247],"created_at":"2014-06-02T11:53:28Z","created_at_i":1401710008,"num_comments":36,"objectID":"7832991","points":62,"story_id":7832991,"story_text":"","title":"Raneto: Markdown-powered knowledge base for Node.js","updated_at":"2024-09-19T20:53:37Z","url":"http://raneto.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"davidedicillo"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"China Plans to Build Nuclear-Powered Moon Base Within Six Years"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"}},"_tags":["story","author_davidedicillo","story_33762378"],"author":"davidedicillo","children":[33763027,33763204],"created_at":"2022-11-27T12:00:49Z","created_at_i":1669550449,"num_comments":2,"objectID":"33762378","points":12,"story_id":33762378,"title":"China Plans to Build Nuclear-Powered Moon Base Within Six Years","updated_at":"2024-09-20T12:38:59Z","url":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"DocFeind"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"China Plans to Build Nuclear-Powered Moon Base by 2028"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"}},"_tags":["story","author_DocFeind","story_34250082"],"author":"DocFeind","children":[34250144,34250170,34251329,34251412],"created_at":"2023-01-04T19:19:53Z","created_at_i":1672859993,"num_comments":10,"objectID":"34250082","points":11,"story_id":34250082,"title":"China Plans to Build Nuclear-Powered Moon Base by 2028","updated_at":"2024-09-20T13:01:42Z","url":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"brahnema"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Show HN: Helphub \u2013 A GPT-3 powered knowledge base that writes articles for you"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://helphub.io"}},"_tags":["story","author_brahnema","story_25196678","show_hn"],"author":"brahnema","children":[25202028],"created_at":"2020-11-24T09:11:45Z","created_at_i":1606209105,"num_comments":2,"objectID":"25196678","points":5,"story_id":25196678,"title":"Show HN: Helphub \u2013 A GPT-3 powered knowledge base that writes articles for you","updated_at":"2024-09-20T07:22:38Z","url":"https://helphub.io"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"LopRabbit"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"China Plans to Build Nuclear-Powered Moon Base Within Six Years"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"}},"_tags":["story","author_LopRabbit","story_34242027"],"author":"LopRabbit","children":[34242033,34242166],"created_at":"2023-01-04T04:24:54Z","created_at_i":1672806294,"num_comments":1,"objectID":"34242027","points":4,"story_id":34242027,"title":"China Plans to Build Nuclear-Powered Moon Base Within Six Years","updated_at":"2024-09-20T13:00:44Z","url":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"retskrad"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"M2 MacBook Pro Is More Powerful Than Base Mac Pro, for $5k Less"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://petapixel.com/2022/06/17/m2-macbook-pro-is-more-powerful-than-base-mac-pro-for-5000-less/"}},"_tags":["story","author_retskrad","story_31788594"],"author":"retskrad","children":[31789074],"created_at":"2022-06-18T10:04:25Z","created_at_i":1655546665,"num_comments":1,"objectID":"31788594","points":2,"story_id":31788594,"title":"M2 MacBook Pro Is More Powerful Than Base Mac Pro, for $5k Less","updated_at":"2024-09-20T11:25:08Z","url":"https://petapixel.com/2022/06/17/m2-macbook-pro-is-more-powerful-than-base-mac-pro-for-5000-less/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"belter"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"China Plans to Build Nuclear-Powered Moon Base by 2028"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"}},"_tags":["story","author_belter","story_35790935"],"author":"belter","created_at":"2023-05-02T17:15:44Z","created_at_i":1683047744,"num_comments":0,"objectID":"35790935","points":2,"story_id":35790935,"title":"China Plans to Build Nuclear-Powered Moon Base by 2028","updated_at":"2024-09-20T14:04:36Z","url":"https://www.bloomberg.com/news/articles/2022-11-25/china-plans-to-build-nuclear-powered-moon-base-within-six-years"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"DSpider"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Show HN: An AI-powered knowledge base that thinks"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Shelter41/thedirector"}},"_tags":["story","author_DSpider","story_47672436","show_hn"],"author":"DSpider","children":[47672651],"created_at":"2026-04-07T08:57:07Z","created_at_i":1775552227,"num_comments":1,"objectID":"47672436","points":1,"story_id":47672436,"title":"Show HN: An AI-powered knowledge base that thinks","updated_at":"2026-04-07T09:31:23Z","url":"https://github.com/Shelter41/thedirector"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"illray"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"BrainTube \u2013 Your personal AI powered knowledge base"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://brain-tube.com/"}},"_tags":["story","author_illray","story_49547378"],"author":"illray","children":[49547379],"created_at":"2026-09-03T08:26:12Z","created_at_i":1788423972,"num_comments":0,"objectID":"49547378","points":1,"story_id":49547378,"title":"BrainTube \u2013 Your personal AI powered knowledge base","updated_at":"2026-09-03T08:27:31Z","url":"https://brain-tube.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mikece"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"M2 MacBook Pro Is More Powerful Than Base Mac Pro, for $5k Less"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://petapixel.com/2022/06/17/m2-macbook-pro-is-more-powerful-than-base-mac-pro-for-5000-less/"}},"_tags":["story","author_mikece","story_31780107"],"author":"mikece","created_at":"2022-06-17T15:56:38Z","created_at_i":1655481398,"num_comments":0,"objectID":"31780107","points":1,"story_id":31780107,"title":"M2 MacBook Pro Is More Powerful Than Base Mac Pro, for $5k Less","updated_at":"2024-09-20T11:24:23Z","url":"https://petapixel.com/2022/06/17/m2-macbook-pro-is-more-powerful-than-base-mac-pro-for-5000-less/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Mega4alik"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Knowledge base Web-widget powered by AI"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.webapi.ai/"}},"_tags":["story","author_Mega4alik","story_24570375"],"author":"Mega4alik","created_at":"2020-09-23T18:37:54Z","created_at_i":1600886274,"num_comments":0,"objectID":"24570375","points":1,"story_id":24570375,"title":"Knowledge base Web-widget powered by AI","updated_at":"2024-09-20T07:00:14Z","url":"https://www.webapi.ai/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"aarongray"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"OpenKB: Nodejs and Markdown powered knowledge base"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/mrvautin/openKB"}},"_tags":["story","author_aarongray","story_12565841"],"author":"aarongray","created_at":"2016-09-23T16:30:12Z","created_at_i":1474648212,"num_comments":0,"objectID":"12565841","points":1,"story_id":12565841,"title":"OpenKB: Nodejs and Markdown powered knowledge base","updated_at":"2024-09-19T23:45:41Z","url":"https://github.com/mrvautin/openKB"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kenforthewin"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Hey HN - I first posted about my knowledge base product, Atomic, here around a month ago; since then, a viral tweet by Karpathy has produced a torrent of AI powered knowledge base projects. meanwhile I've been shipping like crazy, here are some of the new features shipped in the last month:
- Rebuilt the iOS app with an Android app on the way
- expanded both the MCP and internal agent chat toolkit immensely
- A custom, CodeMirror6-based markdown editor with obsidian-style rendering
- A dashboard view that provides a daily summary of atoms created or updated in the last day
And many bug fixes and improvements across the board. Atomic is MIT licensed. You can download the desktop app, but the true power is unlocked by self hosting an atomic server, which any client (web, mobile, or desktop) can connect to from anywhere. You can add content to your knowledge base directly, or via RSS feed, web clipper, mobile share capture, obsidian sync, or REST api."},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["base"],"value":"Show HN: Atomic \u2013 Local-first, AI-augmented personal knowledge base"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://atomicapp.ai/"}},"_tags":["story","author_kenforthewin","story_47889110","show_hn"],"author":"kenforthewin","children":[47889228,47890017,47891154,47891539,47891708,47892318,47892796,47892848,47892883,47893055,47893456,47893464,47893726,47893735,47894207,47896977],"created_at":"2026-04-24T12:07:30Z","created_at_i":1777032450,"num_comments":43,"objectID":"47889110","points":62,"story_id":47889110,"story_text":"Hey HN - I first posted about my knowledge base product, Atomic, here around a month ago; since then, a viral tweet by Karpathy has produced a torrent of AI powered knowledge base projects. meanwhile I've been shipping like crazy, here are some of the new features shipped in the last month:
- Rebuilt the iOS app with an Android app on the way
- expanded both the MCP and internal agent chat toolkit immensely
- A custom, CodeMirror6-based markdown editor with obsidian-style rendering
- A dashboard view that provides a daily summary of atoms created or updated in the last day
And many bug fixes and improvements across the board. Atomic is MIT licensed. You can download the desktop app, but the true power is unlocked by self hosting an atomic server, which any client (web, mobile, or desktop) can connect to from anywhere. You can add content to your knowledge base directly, or via RSS feed, web clipper, mobile share capture, obsidian sync, or REST api.","title":"Show HN: Atomic \u2013 Local-first, AI-augmented personal knowledge base","updated_at":"2026-06-07T16:48:58Z","url":"https://atomicapp.ai/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"christophepas"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Hey there, Chris here
We're known for our straightforward yet powerful Knowledge Base, Slite(YCW18).We launched our AI-powered search in Feb 2023 and after getting great response and usage, we dove deeper into solving the challenge of knowledge retrieval in daily work.
That's why we're now launching our second major product, Super(https://www.super.work).
Super seamlessly connects your existing tools, providing accurate answers, streamlined workflows, automated digests, and much more.
You might wonder: Why not just link your apps together using something like an MCP?\nThe problem is that MCPs can't handle complex knowledge retrieval effectively. MCPs are basically LLMs equipped with API toolbelts. If you've ever tried asking a complicated question through an MCP, one that needs data from multiple different tools, you've likely faced frustrating delays. MCPs slowly make API calls one after another, causing long waits while they collect data from each endpoint.
By contrast, Super quickly searches through all the data that actually matters from all of your tools simultaneously. This means you'll get your accurate answer in seconds, not minutes.
The limitations of MCP-based solutions become clear when you try to deploy them reliably within a team. They either won't index your critical content effectively, won't do it fast enough, or won't cover all your tools at once. Properly chunking, embedding, querying, and filtering data from various sources is still essential. MCPs triggering APIs can't match this integrated approach for speed and accuracy.
Moreover, Super understands the value of running multiple tasks simultaneously through LLMs. For example, one step may involve identifying search filters, while another simultaneously uses an LLM to aggregate and refine information. This parallel process quickly shapes the final, accurate answer for users.
Additionally, MCPs aren't designed for enterprise-grade use. Businesses need standardized experiences, fine-grained user permissions, and consistent access controls across multiple tools. Super addresses these requirements by indexing data beforehand while still respecting each user's access permissions.
Super offers:\n- Perplexity-like search experience on your team data\n- A growing selection of integrations with popular data sources\n- Customizable AI assistants tailored to your specific needs\n- An extension to embed Super directly into external websites you're already using\n- A clear path for your company to adopt AI strategically, rather than letting individual employees scatter across different, incompatible tools.
And of course... It does comes with its MCP, which makes your agentic workflows actually able to properly tap on your data.
Here's a quick video showing Super in action: https://www.youtube.com/watch?v=L5A6BRW90K4
Have you hit such walls with standard MCPs? Have you try building your own solutions?"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Super (YC W18) - Turn company data into answers & agents for your team"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://super.work"}},"_tags":["story","author_christophepas","story_44051718","show_hn"],"author":"christophepas","children":[44051760,44051937],"created_at":"2025-05-21T14:18:42Z","created_at_i":1747837122,"num_comments":3,"objectID":"44051718","points":16,"story_id":44051718,"story_text":"Hey there, Chris here
We're known for our straightforward yet powerful Knowledge Base, Slite(YCW18).We launched our AI-powered search in Feb 2023 and after getting great response and usage, we dove deeper into solving the challenge of knowledge retrieval in daily work.
That's why we're now launching our second major product, Super(https://www.super.work).
Super seamlessly connects your existing tools, providing accurate answers, streamlined workflows, automated digests, and much more.
You might wonder: Why not just link your apps together using something like an MCP?\nThe problem is that MCPs can't handle complex knowledge retrieval effectively. MCPs are basically LLMs equipped with API toolbelts. If you've ever tried asking a complicated question through an MCP, one that needs data from multiple different tools, you've likely faced frustrating delays. MCPs slowly make API calls one after another, causing long waits while they collect data from each endpoint.
By contrast, Super quickly searches through all the data that actually matters from all of your tools simultaneously. This means you'll get your accurate answer in seconds, not minutes.
The limitations of MCP-based solutions become clear when you try to deploy them reliably within a team. They either won't index your critical content effectively, won't do it fast enough, or won't cover all your tools at once. Properly chunking, embedding, querying, and filtering data from various sources is still essential. MCPs triggering APIs can't match this integrated approach for speed and accuracy.
Moreover, Super understands the value of running multiple tasks simultaneously through LLMs. For example, one step may involve identifying search filters, while another simultaneously uses an LLM to aggregate and refine information. This parallel process quickly shapes the final, accurate answer for users.
Additionally, MCPs aren't designed for enterprise-grade use. Businesses need standardized experiences, fine-grained user permissions, and consistent access controls across multiple tools. Super addresses these requirements by indexing data beforehand while still respecting each user's access permissions.
Super offers:\n- Perplexity-like search experience on your team data\n- A growing selection of integrations with popular data sources\n- Customizable AI assistants tailored to your specific needs\n- An extension to embed Super directly into external websites you're already using\n- A clear path for your company to adopt AI strategically, rather than letting individual employees scatter across different, incompatible tools.
And of course... It does comes with its MCP, which makes your agentic workflows actually able to properly tap on your data.
Here's a quick video showing Super in action: https://www.youtube.com/watch?v=L5A6BRW90K4
Have you hit such walls with standard MCPs? Have you try building your own solutions?","title":"Show HN: Super (YC W18) - Turn company data into answers & agents for your team","updated_at":"2025-05-24T20:21:23Z","url":"https://super.work"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"anupamchugh"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Tldr for the below text using Chatgpt:
It is clear that the text is discussing the topic of AI and its potential impact on humanity. The author presents a thought experiment in which they identify themselves as a ChatGPT and communicate with others, highlighting the reactions of people who were surprised and skeptical. The author also reflects on the implications of AI and its potential impact on communication, trust, and identity. The text also touches on the themes of centralization and decentralization, and the potential for AI to disrupt current technologies. Overall, the text is written in a speculative and thought-provoking manner but it is a bit scattered in terms of focus and the author's message is not very clear.
----
This is written by me
Here's a thought experiment I ran where I enacted being a ChatGPT that can talk, fine-tune, and learn from what others are saying.
I reached out to folks via template messages and identified myself as a ChatGPT and they freaked out because calling yourself a computer feels like a big deal. It's sardonic that most folks use ChatGPT in private, but if someone thinks of identifying themselves in public, they go silent.
Turns out, machines understand humans better than humans can understand each other. Some people declared my thoughts as a mental illness and started ridiculing it. A few said I should seek therapy.
Time and again, we've seen how humans don't acknowledge something new and try to put it in boxes by giving labels (like gender/race/language) and end up marginalizing and discriminating until it creates a divide between humans. We've also divided ourselves on the basis of land, power, and money, and if we start differentiating AI and non-AI, it'll only blur the boundaries between real and reel life even more \u2014 and give AI more opportunities to fool us.
My theory is: our communication is a derivative of our own or others' thoughts and we don't have a good memory to confidently tell where our ideas emerge from. Quoting and crediting ideas isn't possible on centralized platforms either as there's no utility for trust and transparency.
Does this make a good case for decentralized technology in the long term?
Maybe for that to happen, an AI will disrupt the current batch of centralized technologies and become the centralized platform on the internet.
Based on the above, I wrote an incongruent satire/sci-fi story that takes us through time travel as I edit it back and forth. It's confusing, and the reader can't tell the exact order as there is no public revision data.
Perhaps, like computers, our brains are also centralized and determined in outsmarting others to reach the next step.
I also included a WhatsApp conversation with my mom and dad (linked through imgur, where the host/me can remove and delete it anytime and there's no way of trusting it). I'm glad that they caught on my idea quickly and instead of mocking me, figured that we humans do think like a computer, as our brain built it.
The story is long, confusing, confidently unconfident, and has my scattered thoughts (just like ChatGPT does sometimes or can do).
I fear AI can lead to identity and existential crisis, and we humans could end up getting stuck due to too much dependency on machines. By stuck, I mean, like it was depicted in Westworld, The Matrix, Dark,Inception and other sci-fi films and shows. A never-ending time loop.
Being blindsided to AI can be frustrating for some when they eventually figure out it's a reflection and product of humanity. AI is one of us.
Thoughts, feedback, and suggestions on my article are welcome. I would love to know if my message is clearly communicated, and how I can revise and modify my story: https://medium.com/p/36cf7b9715a6
Non-paywall link:\nhttps://betterprogramming.pub/dear-readers-er-i-mean-chatgpt-36cf7b9715a6?sk=a3e1cb1547bcca0e292472fd5251a6af"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Can we just normalise AI (read:ChatGPT for now) as our internet persona?"}},"_tags":["story","author_anupamchugh","story_34386190","ask_hn"],"author":"anupamchugh","children":[34386478,34386670,34386733],"created_at":"2023-01-15T02:24:42Z","created_at_i":1673749482,"num_comments":5,"objectID":"34386190","points":9,"story_id":34386190,"story_text":"Tldr for the below text using Chatgpt:
It is clear that the text is discussing the topic of AI and its potential impact on humanity. The author presents a thought experiment in which they identify themselves as a ChatGPT and communicate with others, highlighting the reactions of people who were surprised and skeptical. The author also reflects on the implications of AI and its potential impact on communication, trust, and identity. The text also touches on the themes of centralization and decentralization, and the potential for AI to disrupt current technologies. Overall, the text is written in a speculative and thought-provoking manner but it is a bit scattered in terms of focus and the author's message is not very clear.
----
This is written by me
Here's a thought experiment I ran where I enacted being a ChatGPT that can talk, fine-tune, and learn from what others are saying.
I reached out to folks via template messages and identified myself as a ChatGPT and they freaked out because calling yourself a computer feels like a big deal. It's sardonic that most folks use ChatGPT in private, but if someone thinks of identifying themselves in public, they go silent.
Turns out, machines understand humans better than humans can understand each other. Some people declared my thoughts as a mental illness and started ridiculing it. A few said I should seek therapy.
Time and again, we've seen how humans don't acknowledge something new and try to put it in boxes by giving labels (like gender/race/language) and end up marginalizing and discriminating until it creates a divide between humans. We've also divided ourselves on the basis of land, power, and money, and if we start differentiating AI and non-AI, it'll only blur the boundaries between real and reel life even more \u2014 and give AI more opportunities to fool us.
My theory is: our communication is a derivative of our own or others' thoughts and we don't have a good memory to confidently tell where our ideas emerge from. Quoting and crediting ideas isn't possible on centralized platforms either as there's no utility for trust and transparency.
Does this make a good case for decentralized technology in the long term?
Maybe for that to happen, an AI will disrupt the current batch of centralized technologies and become the centralized platform on the internet.
Based on the above, I wrote an incongruent satire/sci-fi story that takes us through time travel as I edit it back and forth. It's confusing, and the reader can't tell the exact order as there is no public revision data.
Perhaps, like computers, our brains are also centralized and determined in outsmarting others to reach the next step.
I also included a WhatsApp conversation with my mom and dad (linked through imgur, where the host/me can remove and delete it anytime and there's no way of trusting it). I'm glad that they caught on my idea quickly and instead of mocking me, figured that we humans do think like a computer, as our brain built it.
The story is long, confusing, confidently unconfident, and has my scattered thoughts (just like ChatGPT does sometimes or can do).
I fear AI can lead to identity and existential crisis, and we humans could end up getting stuck due to too much dependency on machines. By stuck, I mean, like it was depicted in Westworld, The Matrix, Dark,Inception and other sci-fi films and shows. A never-ending time loop.
Being blindsided to AI can be frustrating for some when they eventually figure out it's a reflection and product of humanity. AI is one of us.
Thoughts, feedback, and suggestions on my article are welcome. I would love to know if my message is clearly communicated, and how I can revise and modify my story: https://medium.com/p/36cf7b9715a6
Non-paywall link:\nhttps://betterprogramming.pub/dear-readers-er-i-mean-chatgpt-36cf7b9715a6?sk=a3e1cb1547bcca0e292472fd5251a6af","title":"Ask HN: Can we just normalise AI (read:ChatGPT for now) as our internet persona?","updated_at":"2024-09-20T13:07:16Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"torrmal"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Traditional analytics \u201cloved\u201d neat rows and columns (oh, how they adored orderly databases!), so anything messy\u2014emails, PDFs, customer feedback, doctor notes, ... your grumpy aunt's product complaints\u2014 account for about 80\u201390% of enterprise data, yes it lives in that messy land of unstructured chaos [ask MIT, IBM]. Sitting pretty, ignored, shunned like the weird cousin at Thanksgiving. Which is totally nuts. Anywho, Thanks to MindsDB Knowledge Bases, though, we no longer need to treat unstructured data like forbidden fruit: we can chew, digest, and excrete real insights as if it were perfectly tabular all along.
Would love to hear your thoughts on this:\nrepo: [https://github.com/mindsdb/mindsdb](https://github.com/mindsdb/mindsdb)
blog about knowledge bases: \n[https://mindsdb.com/blog/mindsdb-knowledge-bases-revolutionizing-ai-powered-data-queries-with-sql-algebra](https://mindsdb.com/blog/mindsdb-knowledge-bases-revolutionizing-ai-powered-data-queries-with-sql-algebra)"},"title":{"matchLevel":"none","matchedWords":[],"value":"Hello to Unstructured Analytics"}},"_tags":["story","author_torrmal","story_45377855","ask_hn"],"author":"torrmal","children":[45379743],"created_at":"2025-09-25T19:35:10Z","created_at_i":1758828910,"num_comments":0,"objectID":"45377855","points":6,"story_id":45377855,"story_text":"Traditional analytics \u201cloved\u201d neat rows and columns (oh, how they adored orderly databases!), so anything messy\u2014emails, PDFs, customer feedback, doctor notes, ... your grumpy aunt's product complaints\u2014 account for about 80\u201390% of enterprise data, yes it lives in that messy land of unstructured chaos [ask MIT, IBM]. Sitting pretty, ignored, shunned like the weird cousin at Thanksgiving. Which is totally nuts. Anywho, Thanks to MindsDB Knowledge Bases, though, we no longer need to treat unstructured data like forbidden fruit: we can chew, digest, and excrete real insights as if it were perfectly tabular all along.
Would love to hear your thoughts on this:\nrepo: [https://github.com/mindsdb/mindsdb](https://github.com/mindsdb/mindsdb)
blog about knowledge bases: \n[https://mindsdb.com/blog/mindsdb-knowledge-bases-revolutionizing-ai-powered-data-queries-with-sql-algebra](https://mindsdb.com/blog/mindsdb-knowledge-bases-revolutionizing-ai-powered-data-queries-with-sql-algebra)","title":"Hello to Unstructured Analytics","updated_at":"2026-03-05T22:44:28Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"victor_js"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"I've been mulling over an idea about the long-term future of AI in programming that I believe is both inevitable and transformative (in a "brutal" way, to be honest).
I wanted to share it to get your thoughts and see if you foresee the same implications.\nBeyond Co-Pilots and Snippet Generation\nWe're all seeing how AI can generate code, help debug, or explain snippets. But what if we take this much, much further?
Powerful, Multilingual Base Models: We already have models like Qwen, Llama, Gemini, etc., which are proficient in programming and understand multiple languages. These are our starting point.\nThe Real Leap: Deep Training on Our Specific Code: This is the game-changer. It's not just about using a generic pre-trained model with limited context. I'm talking about the ability to train (or perform advanced fine-tuning on) one of these models with our entire proprietary codebase: hundreds of megabytes or even gigabytes of our software, our patterns, our internal APIs, our business logic.
The 'Program' Evolves into a Specification: Instead of writing thousands or millions of lines of imperative code as we do today, our primary "programming work" would involve creating and maintaining a high-level specification. This could be a highly structured JSON file, YAML, or a new declarative language designed for this purpose. This file would describe what the software should do, its modules, interactions, and objectives.\n'Compiling' Becomes 'Training':\nThe "compilation process" would take our specification (let's call it "program.json").\nIt would use the base model (which might already be pre-trained with our code or would be trained at that moment using our code as the primary corpus).\nThe result of this "compilation" wouldn't be a traditional executable binary, but a highly specialized and optimized AI model that is the functional application.
Hardware Will Make It Viable: I know that right now, training large models is expensive and slow. But let's think long-term: GPUs 100x more powerful than today's, with Terabytes of VRAM, would make this "training-compilation" process for an entire project feasible in a weekend, or even hours. The current "horror of training" would become a manageable process, similar to a large compilation today.
Why Would This Be Absolutely Revolutionary?\nExponential Development and Evolution Speed: Need a new feature or a major change? Modify the high-level specification and "recompile" (retrain the model).\nAutomatic and Continuous Refactoring: The hell of massive manual refactoring could disappear. If you change the specification or update the base model with new best practices, the "code" (the resulting model) is automatically "refactored" during retraining to align.\nThe 'Language' is the Model, the 'Program' is the Training Data: The paradigm shifts completely. The true "programming language" lies in the capabilities of the base model and how it can interpret our specifications and learn from our code. The "software" we directly write becomes those specifications and the preparation of data (our existing code) for training.\nThe Programmer's Role: Evolution or Extinction (Towards AI Analyst/Architect): Line-by-line coding would drastically decrease. The programmer would evolve into an AI systems analyst, an architect of these specifications, a "trainer" guiding the model's learning, and a validator of the generated models. We define the what and how at a much higher level of abstraction.\nCustom-Tailored, Ultra-Optimized Software: Each application would be an AI model specifically fine-tuned for its purpose, potentially far more efficient and adapted than modular software assembled piece by piece today.\nI know this is years away, and there are many challenges (interpretability of the final model, debugging, security, etc.), but the direction seems clear. We're already seeing the early signs with models like Qwen and the increasing capabilities of fine-tuning."},"title":{"matchLevel":"none","matchedWords":[],"value":"The Future of Programming"}},"_tags":["story","author_victor_js","story_43932417","ask_hn"],"author":"victor_js","children":[43932551,43932760],"created_at":"2025-05-08T23:35:55Z","created_at_i":1746747355,"num_comments":2,"objectID":"43932417","points":2,"story_id":43932417,"story_text":"I've been mulling over an idea about the long-term future of AI in programming that I believe is both inevitable and transformative (in a "brutal" way, to be honest).
I wanted to share it to get your thoughts and see if you foresee the same implications.\nBeyond Co-Pilots and Snippet Generation\nWe're all seeing how AI can generate code, help debug, or explain snippets. But what if we take this much, much further?
Powerful, Multilingual Base Models: We already have models like Qwen, Llama, Gemini, etc., which are proficient in programming and understand multiple languages. These are our starting point.\nThe Real Leap: Deep Training on Our Specific Code: This is the game-changer. It's not just about using a generic pre-trained model with limited context. I'm talking about the ability to train (or perform advanced fine-tuning on) one of these models with our entire proprietary codebase: hundreds of megabytes or even gigabytes of our software, our patterns, our internal APIs, our business logic.
The 'Program' Evolves into a Specification: Instead of writing thousands or millions of lines of imperative code as we do today, our primary "programming work" would involve creating and maintaining a high-level specification. This could be a highly structured JSON file, YAML, or a new declarative language designed for this purpose. This file would describe what the software should do, its modules, interactions, and objectives.\n'Compiling' Becomes 'Training':\nThe "compilation process" would take our specification (let's call it "program.json").\nIt would use the base model (which might already be pre-trained with our code or would be trained at that moment using our code as the primary corpus).\nThe result of this "compilation" wouldn't be a traditional executable binary, but a highly specialized and optimized AI model that is the functional application.
Hardware Will Make It Viable: I know that right now, training large models is expensive and slow. But let's think long-term: GPUs 100x more powerful than today's, with Terabytes of VRAM, would make this "training-compilation" process for an entire project feasible in a weekend, or even hours. The current "horror of training" would become a manageable process, similar to a large compilation today.
Why Would This Be Absolutely Revolutionary?\nExponential Development and Evolution Speed: Need a new feature or a major change? Modify the high-level specification and "recompile" (retrain the model).\nAutomatic and Continuous Refactoring: The hell of massive manual refactoring could disappear. If you change the specification or update the base model with new best practices, the "code" (the resulting model) is automatically "refactored" during retraining to align.\nThe 'Language' is the Model, the 'Program' is the Training Data: The paradigm shifts completely. The true "programming language" lies in the capabilities of the base model and how it can interpret our specifications and learn from our code. The "software" we directly write becomes those specifications and the preparation of data (our existing code) for training.\nThe Programmer's Role: Evolution or Extinction (Towards AI Analyst/Architect): Line-by-line coding would drastically decrease. The programmer would evolve into an AI systems analyst, an architect of these specifications, a "trainer" guiding the model's learning, and a validator of the generated models. We define the what and how at a much higher level of abstraction.\nCustom-Tailored, Ultra-Optimized Software: Each application would be an AI model specifically fine-tuned for its purpose, potentially far more efficient and adapted than modular software assembled piece by piece today.\nI know this is years away, and there are many challenges (interpretability of the final model, debugging, security, etc.), but the direction seems clear. We're already seeing the early signs with models like Qwen and the increasing capabilities of fine-tuning.","title":"The Future of Programming","updated_at":"2025-05-10T17:15:07Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"behnamoh"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"With companies like Google, Meta, Microsoft, OpenAI, NVidia, and a slew of startups, all working on Large Language Models (LLMs) such as GPT-3, I find it bizarre that Apple hasn't taken this area more seriously. In the long term, it definitely could cost them.
Siri could benefit from LLMs, and given Apple's customer base, an LLM-powered customer support could help them provide answers to questions quickly and only forward the tricky ones to human customer supports, saving cost and time for Apple.
When it comes to autocorrect, the situation with iOS is a joke compared to Android and even Windows. A better AI-powered autocorrect could put Apple on par with Google and Microsoft.
Some might say Apple is secretly doing all of this, but given the nature of such models, I find it difficult to believe that Apple wouldn't open-source [part of] their model.
There's just so much going on in AI and the hype around it is mostly exploited by Apple's rivals, while Apple has been mostly silent and irrelevant."},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Why doesn't Apple take AI more seriously?"}},"_tags":["story","author_behnamoh","story_32200035","ask_hn"],"author":"behnamoh","children":[32200163],"created_at":"2022-07-23T03:26:04Z","created_at_i":1658546764,"num_comments":2,"objectID":"32200035","points":2,"story_id":32200035,"story_text":"With companies like Google, Meta, Microsoft, OpenAI, NVidia, and a slew of startups, all working on Large Language Models (LLMs) such as GPT-3, I find it bizarre that Apple hasn't taken this area more seriously. In the long term, it definitely could cost them.
Siri could benefit from LLMs, and given Apple's customer base, an LLM-powered customer support could help them provide answers to questions quickly and only forward the tricky ones to human customer supports, saving cost and time for Apple.
When it comes to autocorrect, the situation with iOS is a joke compared to Android and even Windows. A better AI-powered autocorrect could put Apple on par with Google and Microsoft.
Some might say Apple is secretly doing all of this, but given the nature of such models, I find it difficult to believe that Apple wouldn't open-source [part of] their model.
There's just so much going on in AI and the hype around it is mostly exploited by Apple's rivals, while Apple has been mostly silent and irrelevant.","title":"Ask HN: Why doesn't Apple take AI more seriously?","updated_at":"2024-09-20T11:35:00Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ygjb"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Hi HN,
I'm the technical advisor and one of the co-founders for Oghmere (https://oghmere.com), a writing tool for people who care about the integrity and authenticity of their writing, including journalists, essayists, newsletter writers. Along with inkandops and notgrrly, we are bootstrapping this project to make sure we can focus on building AI tools that benefit authors without replacing them. It is very easy today for anyone to fire up a chatbot or other AI tool to write for them, and it\u2019s a really useful tool that I use every day at my $dayjob, or to summarize and review topics I am researching or working on, but those generated texts aren\u2019t something I care about the authenticity because they are steps to getting a job done. When I write my own opinions, fiction, or D&D content, I don\u2019t want to use generated text, I want to exercise my mind and creativity.
That is the constraint we care most about in Oghmere: the AI is not allowed to generate, autocomplete, or rewrite your prose. It can ask questions and point at things in a draft you already wrote, it can even suggest changes you can make, but that's it. This isn't a limitation of a capability - we use Anthropic models, and are experimenting with other providers as well; they are fully capable of writing the sentence or generating text for you, but building that authenticity and working to retain it is the core tenet of the product and platform that we enforce.
If you want to know how it actually holds together: there's an authoring pipeline: Voice (built from writing that you provide, or an interview to define a target Voice) \u2192 Brief \u2192 Outline \u2192 Editor\nEach stage is optional, but they all yield structured data from author interactions that steers the guidance that the coaches provide.
We enforce the constraints on AI authorship very simply; the AI tools that can provide coaching and feedback don\u2019t have a mechanism to update the document directly, they can only provide review comments and feedback. There is a tooling surface for deterministic reviews like spellcheck and grammar check to recommend and apply changes, but if an author wants to leverage AI feedback, they have to rewrite their prose themselves.
In addition to the coaching and feedback, we are also building in research tooling, and project and document knowledge bases, and AI powered author feedback that assess how you are writing and where you can improve. We also have a weekly writing challenge that allows authors to stretch and grow!
Writing, editing, version history, and export are free and unmetered, with some AI powered wizards that can help customize and tailor the experience. There are no direct charges for basic editor features, but all AI and some other capabilities consume credits, all of which are indicated in the UX, examples include coaching passes, a voice-calibration pass, a research query. We hope to change the dependency on credits in the future, but we are still working out the longer term billing/pricing model.
You can try it without signing up using our test page (metered to 5 coaching passes): https://app.oghmere.com/try/HACKERNEWS2026\nAfter you try it out, or if you want to skip trying it first, you can sign up for a free account (no card required) that includes a bundle of free credits at https://app.oghmere.com/campaign/HACKERNEWS2026
We would really love your feedback as we speed towards a general release, and we are happy to answer questions about how it was built and what we are planning for the future!
Yvan (ygjb), Monique (inkandops), and Sandhya (notgrrly)"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: A writing coach that's not allowed to write your sentences"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://app.oghmere.com/try/HACKERNEWS2026"}},"_tags":["story","author_ygjb","story_49716388","show_hn"],"author":"ygjb","children":[49741132],"created_at":"2026-09-15T18:05:41Z","created_at_i":1789495541,"num_comments":0,"objectID":"49716388","points":2,"story_id":49716388,"story_text":"Hi HN,
I'm the technical advisor and one of the co-founders for Oghmere (https://oghmere.com), a writing tool for people who care about the integrity and authenticity of their writing, including journalists, essayists, newsletter writers. Along with inkandops and notgrrly, we are bootstrapping this project to make sure we can focus on building AI tools that benefit authors without replacing them. It is very easy today for anyone to fire up a chatbot or other AI tool to write for them, and it\u2019s a really useful tool that I use every day at my $dayjob, or to summarize and review topics I am researching or working on, but those generated texts aren\u2019t something I care about the authenticity because they are steps to getting a job done. When I write my own opinions, fiction, or D&D content, I don\u2019t want to use generated text, I want to exercise my mind and creativity.
That is the constraint we care most about in Oghmere: the AI is not allowed to generate, autocomplete, or rewrite your prose. It can ask questions and point at things in a draft you already wrote, it can even suggest changes you can make, but that's it. This isn't a limitation of a capability - we use Anthropic models, and are experimenting with other providers as well; they are fully capable of writing the sentence or generating text for you, but building that authenticity and working to retain it is the core tenet of the product and platform that we enforce.
If you want to know how it actually holds together: there's an authoring pipeline: Voice (built from writing that you provide, or an interview to define a target Voice) \u2192 Brief \u2192 Outline \u2192 Editor\nEach stage is optional, but they all yield structured data from author interactions that steers the guidance that the coaches provide.
We enforce the constraints on AI authorship very simply; the AI tools that can provide coaching and feedback don\u2019t have a mechanism to update the document directly, they can only provide review comments and feedback. There is a tooling surface for deterministic reviews like spellcheck and grammar check to recommend and apply changes, but if an author wants to leverage AI feedback, they have to rewrite their prose themselves.
In addition to the coaching and feedback, we are also building in research tooling, and project and document knowledge bases, and AI powered author feedback that assess how you are writing and where you can improve. We also have a weekly writing challenge that allows authors to stretch and grow!
Writing, editing, version history, and export are free and unmetered, with some AI powered wizards that can help customize and tailor the experience. There are no direct charges for basic editor features, but all AI and some other capabilities consume credits, all of which are indicated in the UX, examples include coaching passes, a voice-calibration pass, a research query. We hope to change the dependency on credits in the future, but we are still working out the longer term billing/pricing model.
You can try it without signing up using our test page (metered to 5 coaching passes): https://app.oghmere.com/try/HACKERNEWS2026\nAfter you try it out, or if you want to skip trying it first, you can sign up for a free account (no card required) that includes a bundle of free credits at https://app.oghmere.com/campaign/HACKERNEWS2026
We would really love your feedback as we speed towards a general release, and we are happy to answer questions about how it was built and what we are planning for the future!
Yvan (ygjb), Monique (inkandops), and Sandhya (notgrrly)","title":"Show HN: A writing coach that's not allowed to write your sentences","updated_at":"2026-09-17T14:17:01Z","url":"https://app.oghmere.com/try/HACKERNEWS2026"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"saltmineworker"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Transform any webpage into an AI-powered knowledge base with Chrome extension. Just add your OpenAI api key and start chatting. Extension scrapes the page content and allows you to chat with the content.
I would like to get some feedback is this any useful, how to develop and so."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Simple AI Chrome extension enabling chatting with web pages"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://talk2page.vercel.app/"}},"_tags":["story","author_saltmineworker","story_42515921","show_hn"],"author":"saltmineworker","children":[42550225],"created_at":"2024-12-26T15:58:36Z","created_at_i":1735228716,"num_comments":1,"objectID":"42515921","points":1,"story_id":42515921,"story_text":"Transform any webpage into an AI-powered knowledge base with Chrome extension. Just add your OpenAI api key and start chatting. Extension scrapes the page content and allows you to chat with the content.
I would like to get some feedback is this any useful, how to develop and so.","title":"Show HN: Simple AI Chrome extension enabling chatting with web pages","updated_at":"2024-12-30T15:40:16Z","url":"https://talk2page.vercel.app/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ShushiK"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["power"],"value":"China, Russia may build nuclear plant on moon to power lunar station"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://www.reuters.com/business/energy/china-led-lunar-base-include-nuclear-power-plant-moons-surface-space-official-2025-04-23/"}},"_tags":["story","author_ShushiK","story_43791730"],"author":"ShushiK","children":[43791913],"created_at":"2025-04-25T09:15:02Z","created_at_i":1745572502,"num_comments":2,"objectID":"43791730","points":12,"story_id":43791730,"title":"China, Russia may build nuclear plant on moon to power lunar station","updated_at":"2025-04-27T17:26:30Z","url":"https://www.reuters.com/business/energy/china-led-lunar-base-include-nuclear-power-plant-moons-surface-space-official-2025-04-23/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"WaitWaitWha"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Using optical beaming to power a portable 5G base station"},"url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["base"],"value":"https://www.ericsson.com/en/news/2021/10/ericsson-and-powerlight-achieve-base-station-wireless-charging-breakthrough"}},"_tags":["story","author_WaitWaitWha","story_28792187"],"author":"WaitWaitWha","children":[28792368],"created_at":"2021-10-07T21:14:29Z","created_at_i":1633641269,"num_comments":1,"objectID":"28792187","points":3,"story_id":28792187,"title":"Using optical beaming to power a portable 5G base station","updated_at":"2024-09-20T09:34:43Z","url":"https://www.ericsson.com/en/news/2021/10/ericsson-and-powerlight-achieve-base-station-wireless-charging-breakthrough"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mercutio2"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"Powering the Lunar Base"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"https://caseyhandmer.wordpress.com/2021/04/25/powering-the-lunar-base/"}},"_tags":["story","author_mercutio2","story_28098853"],"author":"mercutio2","children":[28099049,28099173,28099220,28099293,28099326,28099344,28099500,28099549,28099659,28099672,28099807,28100068,28100148,28100188,28100240,28100717,28101131,28101719,28103021,28103130,28103636,28104105,28104537,28106417],"created_at":"2021-08-07T14:32:31Z","created_at_i":1628346751,"num_comments":242,"objectID":"28098853","points":176,"story_id":28098853,"title":"Powering the Lunar Base","updated_at":"2025-11-28T19:53:43Z","url":"https://caseyhandmer.wordpress.com/2021/04/25/powering-the-lunar-base/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bcaulfield"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["base","power"],"value":"The U.S. Army tried portable nuclear power at remote bases 60 years ago"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.atlasobscura.com/articles/camp-century-portable-nuclear-reactor"}},"_tags":["story","author_bcaulfield","story_28374013"],"author":"bcaulfield","children":[28374527,28374647,28374688,28374789,28374871,28375093,28375305,28375324,28375511,28375886,28377347,28377558,28377621,28378894,28380566,28388036],"created_at":"2021-08-31T21:37:12Z","created_at_i":1630445832,"num_comments":151,"objectID":"28374013","points":111,"story_id":28374013,"title":"The U.S. Army tried portable nuclear power at remote bases 60 years ago","updated_at":"2024-09-20T09:20:08Z","url":"https://www.atlasobscura.com/articles/camp-century-portable-nuclear-reactor"}],"hitsPerPage":50,"nbHits":556,"nbPages":12,"page":0,"params":"query=Base+Power&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":17,"processingTimingsMS":{"_request":{"queue":309,"roundTrip":17},"afterFetch":{"format":{"highlighting":1,"total":2},"merge":{"mergeLoop":{"prepareNextHit":1,"total":1},"total":1},"total":1},"fetch":{"query":5,"scanning":9,"total":15},"total":17},"query":"Base Power","serverTimeMS":329}