How do you do it, do you have to go looking for database leaks?
It seems that the whole game of technology entrepreneurship is already prearranged."},"title":{"matchLevel":"none","matchedWords":[],"value":"The ridiculousness of asking market research to solopreneur?"}},"_tags":["story","author_andrea81","story_39675304","ask_hn"],"author":"andrea81","children":[39682596,39684714,39707119],"created_at":"2024-03-12T01:47:42Z","created_at_i":1710208062,"num_comments":6,"objectID":"39675304","points":4,"story_id":39675304,"story_text":"It doesn't make sense. Incubators asking for competitive analysis, market size, etc. at pitch desk, when any subscription to these services is expensive for a solopreneur, and not easily accessible (companies like AlphaSense or Bloomberg even ask for a phone call prior to even offering a price).
How do you do it, do you have to go looking for database leaks?
It seems that the whole game of technology entrepreneurship is already prearranged.","title":"The ridiculousness of asking market research to solopreneur?","updated_at":"2024-09-20T16:40:20Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"abbas143"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"Looking for the best AI for a specific purpose? Here\u2019s list of 30 AIs by their strengths, including some top picks like Claude 3, Google Gemini, and Microsoft Copilot. Discover the right AI for your needs, whether it\u2019s for creative tasks, research, business, or personal use. If you know any other standout AIs, let me know in the comments!
Best Assistant\nClaude 3
Best for Live Data\nGoogle Gemini
Most Creative\nMicrosoft Copilot
Best for Research\nPerplexity
Most Personal\nInflection Pi
Best for Social\nxAI Grok
Best for Open Source\nLlama 3
Most Fun\nMetaAI
Best for Business\nIBM Watson
Best for Customer Service\nSalesforce Einstein
Best for Healthcare\nIBM Watson Health
Best for Education\nKnewton
Best for Legal\nROSS Intelligence
Best for Finance\nAlphaSense
Best for Marketing\nHubSpot AI
Best for E-commerce\nShopify\u2019s Kit
Best for Content Creation\nJasper
Best for Video Editing\nRunwayML
Best for Speech Recognition\nNuance
Best for Image Generation\nDALL-E 3 & MidJourney
Best for Virtual Assistants\nAmazon Alexa
Best for Natural Language Processing\nOpenAI GPT-4
Best for Translation\nDeepL
Best for Predictive Analytics\nH2O.ai
Best for Cybersecurity\nDarktrace
Best for Autonomous Vehicles\nWaymo
Best for Robotics\nBoston Dynamics
Best for Text-to-Speech\nGoogle WaveNet
Best for Emotion Recognition\nAffectiva
Best for Game Development\nUnity ML-Agents
Each of these AIs excels in different areas, making them suitable for various applications.
Do you know of any other AIs that I might have missed, or do you have suggestions for AIs with specific strengths or unique capabilities not covered in the list?
Your recommendations would be greatly appreciated!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Top AIs and Their Strengths"}},"_tags":["story","author_abbas143","story_40509303","ask_hn"],"author":"abbas143","created_at":"2024-05-29T07:10:43Z","created_at_i":1716966643,"num_comments":0,"objectID":"40509303","points":1,"story_id":40509303,"story_text":"Looking for the best AI for a specific purpose? Here\u2019s list of 30 AIs by their strengths, including some top picks like Claude 3, Google Gemini, and Microsoft Copilot. Discover the right AI for your needs, whether it\u2019s for creative tasks, research, business, or personal use. If you know any other standout AIs, let me know in the comments!
Best Assistant\nClaude 3
Best for Live Data\nGoogle Gemini
Most Creative\nMicrosoft Copilot
Best for Research\nPerplexity
Most Personal\nInflection Pi
Best for Social\nxAI Grok
Best for Open Source\nLlama 3
Most Fun\nMetaAI
Best for Business\nIBM Watson
Best for Customer Service\nSalesforce Einstein
Best for Healthcare\nIBM Watson Health
Best for Education\nKnewton
Best for Legal\nROSS Intelligence
Best for Finance\nAlphaSense
Best for Marketing\nHubSpot AI
Best for E-commerce\nShopify\u2019s Kit
Best for Content Creation\nJasper
Best for Video Editing\nRunwayML
Best for Speech Recognition\nNuance
Best for Image Generation\nDALL-E 3 & MidJourney
Best for Virtual Assistants\nAmazon Alexa
Best for Natural Language Processing\nOpenAI GPT-4
Best for Translation\nDeepL
Best for Predictive Analytics\nH2O.ai
Best for Cybersecurity\nDarktrace
Best for Autonomous Vehicles\nWaymo
Best for Robotics\nBoston Dynamics
Best for Text-to-Speech\nGoogle WaveNet
Best for Emotion Recognition\nAffectiva
Best for Game Development\nUnity ML-Agents
Each of these AIs excels in different areas, making them suitable for various applications.
Do you know of any other AIs that I might have missed, or do you have suggestions for AIs with specific strengths or unique capabilities not covered in the list?
Your recommendations would be greatly appreciated!","title":"Top AIs and Their Strengths","updated_at":"2024-09-20T17:07:54Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"langtang1996"},"title":{"matchLevel":"none","matchedWords":[],"value":"1B in, 20B out. Apple stays out of the war"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://alphasense.cc/signals/apple-ai/"}},"_tags":["story","author_langtang1996","story_47909633"],"author":"langtang1996","children":[47909700],"created_at":"2026-04-26T12:00:02Z","created_at_i":1777204802,"num_comments":1,"objectID":"47909633","points":1,"story_id":47909633,"title":"1B in, 20B out. Apple stays out of the war","updated_at":"2026-04-26T12:11:07Z","url":"https://alphasense.cc/signals/apple-ai/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"louis_zheng_zs"},"title":{"matchLevel":"none","matchedWords":[],"value":"How to master your mindfulness with EEG technology?"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.producthunt.com/tech/alphasense-meditation-master"}},"_tags":["story","author_louis_zheng_zs","story_11790121"],"author":"louis_zheng_zs","created_at":"2016-05-28T00:53:43Z","created_at_i":1464396823,"num_comments":0,"objectID":"11790121","points":1,"story_id":11790121,"title":"How to master your mindfulness with EEG technology?","updated_at":"2024-09-19T23:19:00Z","url":"https://www.producthunt.com/tech/alphasense-meditation-master"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"matt_d"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"On AlphaTensor\u2019s new matrix multiplication algorithms"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://fgiesen.wordpress.com/2022/10/06/on-alphatensors-new-matrix-multiplication-algorithms/"}},"_tags":["story","author_matt_d","story_33117192"],"author":"matt_d","children":[33117470,33117924,33118232,33118599,33120178,33123911,33123912,33164439],"created_at":"2022-10-07T03:45:20Z","created_at_i":1665114320,"num_comments":76,"objectID":"33117192","points":279,"story_id":33117192,"title":"On AlphaTensor\u2019s new matrix multiplication algorithms","updated_at":"2024-09-20T12:10:50Z","url":"https://fgiesen.wordpress.com/2022/10/06/on-alphatensors-new-matrix-multiplication-algorithms/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"picture"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"The Dec/Compaq Turbo Laser 6 AlphaServer KN7CH Processor"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.cpushack.com/2022/03/26/the-dec-compaq-turbo-laser-6-alphaserver-kn7ch-processor/"}},"_tags":["story","author_picture","story_30815557"],"author":"picture","children":[30816133,30816267,30816711,30816725,30816753,30817091,30818349,30818951,30820702],"created_at":"2022-03-26T21:34:07Z","created_at_i":1648330447,"num_comments":28,"objectID":"30815557","points":57,"story_id":30815557,"title":"The Dec/Compaq Turbo Laser 6 AlphaServer KN7CH Processor","updated_at":"2026-04-15T19:34:42Z","url":"https://www.cpushack.com/2022/03/26/the-dec-compaq-turbo-laser-6-alphaserver-kn7ch-processor/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mr-ai"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"AlphaTensor explained \u2013 Motivation, method, and assessment"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.assemblyai.com/blog/deepminds-alphatensor-explained/"}},"_tags":["story","author_mr-ai","story_33705893"],"author":"mr-ai","children":[33705894,33706891],"created_at":"2022-11-22T14:07:33Z","created_at_i":1669126053,"num_comments":3,"objectID":"33705893","points":5,"story_id":33705893,"title":"AlphaTensor explained \u2013 Motivation, method, and assessment","updated_at":"2024-09-20T12:32:34Z","url":"https://www.assemblyai.com/blog/deepminds-alphatensor-explained/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jonbaer"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"AlphaTensor by DeepMind Explained"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.youtube.com/watch?v=3N3Bl5AA5QU"}},"_tags":["story","author_jonbaer","story_33129336"],"author":"jonbaer","created_at":"2022-10-08T02:37:14Z","created_at_i":1665196634,"num_comments":0,"objectID":"33129336","points":4,"story_id":33129336,"title":"AlphaTensor by DeepMind Explained","updated_at":"2024-09-20T12:12:04Z","url":"https://www.youtube.com/watch?v=3N3Bl5AA5QU"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fanf2"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"The DeepMind AlphaTensor new matrix multiplication algorithms"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://fgiesen.wordpress.com/2022/10/06/on-alphatensors-new-matrix-multiplication-algorithms/"}},"_tags":["story","author_fanf2","story_40737517"],"author":"fanf2","created_at":"2024-06-20T11:42:03Z","created_at_i":1718883723,"num_comments":0,"objectID":"40737517","points":2,"story_id":40737517,"title":"The DeepMind AlphaTensor new matrix multiplication algorithms","updated_at":"2024-09-20T17:15:23Z","url":"https://fgiesen.wordpress.com/2022/10/06/on-alphatensors-new-matrix-multiplication-algorithms/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gyrocode"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"Show HN: jQuery DataTables AlphabetSearch \u2013 A-Z Alphabetical Search"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.gyrocode.com/projects/jquery-datatables-alphabetsearch/"}},"_tags":["story","author_gyrocode","story_14653390","show_hn"],"author":"gyrocode","created_at":"2017-06-28T12:10:16Z","created_at_i":1498651816,"num_comments":0,"objectID":"14653390","points":2,"story_id":14653390,"title":"Show HN: jQuery DataTables AlphabetSearch \u2013 A-Z Alphabetical Search","updated_at":"2024-09-20T00:59:48Z","url":"https://www.gyrocode.com/projects/jquery-datatables-alphabetsearch/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fawce"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"Alphalens \u2013 opensource library for analyzing alpha factors"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.quantopian.com/posts/alphalens-a-new-tool-for-analyzing-alpha-factors"}},"_tags":["story","author_fawce","story_12278275"],"author":"fawce","created_at":"2016-08-12T19:48:59Z","created_at_i":1471031339,"num_comments":0,"objectID":"12278275","points":2,"story_id":12278275,"title":"Alphalens \u2013 opensource library for analyzing alpha factors","updated_at":"2024-09-19T23:36:23Z","url":"https://www.quantopian.com/posts/alphalens-a-new-tool-for-analyzing-alpha-factors"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jacobedawson"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"AlphaTensor finds faster algorithms for many matrix sizes"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://twitter.com/deepmind/status/1577677899108421633"}},"_tags":["story","author_jacobedawson","story_33106856"],"author":"jacobedawson","children":[33106996],"created_at":"2022-10-06T11:19:33Z","created_at_i":1665055173,"num_comments":1,"objectID":"33106856","points":1,"story_id":33106856,"title":"AlphaTensor finds faster algorithms for many matrix sizes","updated_at":"2024-09-20T12:09:30Z","url":"https://twitter.com/deepmind/status/1577677899108421633"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"DarenWatson"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"Why AlphaTensor Failed at 3x3 Matrix Multiplication: The Anchor Barrier"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://zenodo.org/records/18514533"}},"_tags":["story","author_DarenWatson","story_46926695"],"author":"DarenWatson","created_at":"2026-02-07T19:21:34Z","created_at_i":1770492094,"num_comments":0,"objectID":"46926695","points":1,"story_id":46926695,"title":"Why AlphaTensor Failed at 3x3 Matrix Multiplication: The Anchor Barrier","updated_at":"2026-03-05T23:32:06Z","url":"https://zenodo.org/records/18514533"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"che_shr_cat"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://arxiviq.substack.com/p/alpharesearch-accelerating-new-algorithm"}},"_tags":["story","author_che_shr_cat","story_45950167"],"author":"che_shr_cat","created_at":"2025-11-17T01:45:36Z","created_at_i":1763343936,"num_comments":0,"objectID":"45950167","points":1,"story_id":45950167,"title":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models","updated_at":"2026-03-05T23:00:58Z","url":"https://arxiviq.substack.com/p/alpharesearch-accelerating-new-algorithm"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lairv"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"Quantum Circuit Optimization with AlphaTensor"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://arxiv.org/abs/2402.14396"}},"_tags":["story","author_lairv","story_39979306"],"author":"lairv","created_at":"2024-04-09T13:37:57Z","created_at_i":1712669877,"num_comments":0,"objectID":"39979306","points":1,"story_id":39979306,"title":"Quantum Circuit Optimization with AlphaTensor","updated_at":"2024-09-20T16:54:09Z","url":"https://arxiv.org/abs/2402.14396"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"signa11"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"DeepMind's AlphaTensor Explained: Algorithms In Search Of Algorithms"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://www.assemblyai.com/blog/deepminds-alphatensor-explained/"}},"_tags":["story","author_signa11","story_33905839"],"author":"signa11","created_at":"2022-12-08T09:01:04Z","created_at_i":1670490064,"num_comments":0,"objectID":"33905839","points":1,"story_id":33905839,"title":"DeepMind's AlphaTensor Explained: Algorithms In Search Of Algorithms","updated_at":"2024-09-20T12:44:55Z","url":"https://www.assemblyai.com/blog/deepminds-alphatensor-explained/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"OnlineInference"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"AlphaTensor: DeepMind's AI for Efficient Matrix Multiplication Algorithms"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://wandb.ai/telidavies/ml-news/reports/AlphaTensor-DeepMind-s-AI-For-Discovering-Efficient-Matrix-Multiplication-Algorithms--VmlldzoyNzQ2MDQ1"}},"_tags":["story","author_OnlineInference","story_33103371"],"author":"OnlineInference","created_at":"2022-10-06T01:45:15Z","created_at_i":1665020715,"num_comments":0,"objectID":"33103371","points":1,"story_id":33103371,"title":"AlphaTensor: DeepMind's AI for Efficient Matrix Multiplication Algorithms","updated_at":"2024-09-20T12:09:02Z","url":"https://wandb.ai/telidavies/ml-news/reports/AlphaTensor-DeepMind-s-AI-For-Discovering-Efficient-Matrix-Multiplication-Algorithms--VmlldzoyNzQ2MDQ1"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"hodder"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"I'm looking for some open source software to dive into for backtesting trading strategies in/out of sample which produces useful tear sheets, nice built in functions, and quality documentation.
I have looked Quantopian/Alphalens/Zipline, but it seems like it has been left to wither and die outside of Quantopian's online platform. The documentation is frankly terrible.
I have briefly looked at Quantconnect/LEAN and it looks more promising but havent dived in to much detail.
I am also looking at the Quantstrat package in R which appears to be quite promising as well.
I'm involved in the futures markets myself but data access is not an issue. I have Bloomberg so can source my data from them.
So, Quants and traders of Hacker News who aren't using in-house corporate solutions, what are you using?"},"title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Quants and traders: Best OS backtesting platform for trading strategies?"}},"_tags":["story","author_hodder","story_24121164","ask_hn"],"author":"hodder","children":[24122205,24124149,24127117,24143688],"created_at":"2020-08-11T15:15:33Z","created_at_i":1597158933,"num_comments":4,"objectID":"24121164","points":10,"story_id":24121164,"story_text":"I'm looking for some open source software to dive into for backtesting trading strategies in/out of sample which produces useful tear sheets, nice built in functions, and quality documentation.
I have looked Quantopian/Alphalens/Zipline, but it seems like it has been left to wither and die outside of Quantopian's online platform. The documentation is frankly terrible.
I have briefly looked at Quantconnect/LEAN and it looks more promising but havent dived in to much detail.
I am also looking at the Quantstrat package in R which appears to be quite promising as well.
I'm involved in the futures markets myself but data access is not an issue. I have Bloomberg so can source my data from them.
So, Quants and traders of Hacker News who aren't using in-house corporate solutions, what are you using?","title":"Ask HN: Quants and traders: Best OS backtesting platform for trading strategies?","updated_at":"2024-09-20T06:44:18Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gano"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"I\u2019ve been experimenting with a graph-based approach to a classic trading problem: why most dip-buying strategies can\u2019t tell the difference between a temporary overreaction and a genuine structural collapse.
Most systems treat a \u22125% move the same regardless of context. My hypothesis was that where a company sits in the market\u2019s structure matters more than the price move itself.
The engineering idea
I built a knowledge graph of the U.S. public markets with ~207k edges across ~21 relationship types, organized into four layers:
Operational: supply-chain relationships (SUPPLIES_TO, PRODUCES)
Flow: ETF and institutional ownership plumbing
Social: board interlocks (SHARES_DIRECTOR_WITH)
Environmental: geography / competition
For each layer, I compute centrality scores using PageRank-style methods (with inverse-degree weighting to avoid ETF super-nodes dominating).
These structural features are then combined with basic price/volume context and fed into a tree-based model (XGBoost) to rank stocks after sharp drawdowns
What surprised me
When I validated the rankings out-of-sample (2024\u20132025, using Alphalens to avoid look-ahead issues):\n* Operational and Flow edges provided most of the lift\n* Social edges (board interlocks) added much less than I expected\n* Graph features roughly doubled ranking quality versus price-only baselines\nThis wasn\u2019t obvious to me going in \u2014 I expected \u201csocial\u201d connections to matter more.
Why I\u2019m posting
I\u2019m in the process of turning this from a research notebook into a production dashboard, and before I lock in the graph schema I\u2019d love feedback from people who\u2019ve built large graphs in other domains.\nIn particular:\n* Have you seen board-interlock / social edges be predictive elsewhere?\n* Are there graph normalization tricks you\u2019ve found essential at this scale?\n* Any pitfalls you\u2019ve hit when mixing heterogeneous edge types?
Happy to answer questions about the graph construction, centrality calculations, or validation setup."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN:Built a 200k-edge market knowledge graph to filter false dip-buy signals"}},"_tags":["story","author_gano","story_46416991","show_hn"],"author":"gano","children":[46419499],"created_at":"2025-12-29T02:56:52Z","created_at_i":1766977012,"num_comments":2,"objectID":"46416991","points":5,"story_id":46416991,"story_text":"I\u2019ve been experimenting with a graph-based approach to a classic trading problem: why most dip-buying strategies can\u2019t tell the difference between a temporary overreaction and a genuine structural collapse.
Most systems treat a \u22125% move the same regardless of context. My hypothesis was that where a company sits in the market\u2019s structure matters more than the price move itself.
The engineering idea
I built a knowledge graph of the U.S. public markets with ~207k edges across ~21 relationship types, organized into four layers:
Operational: supply-chain relationships (SUPPLIES_TO, PRODUCES)
Flow: ETF and institutional ownership plumbing
Social: board interlocks (SHARES_DIRECTOR_WITH)
Environmental: geography / competition
For each layer, I compute centrality scores using PageRank-style methods (with inverse-degree weighting to avoid ETF super-nodes dominating).
These structural features are then combined with basic price/volume context and fed into a tree-based model (XGBoost) to rank stocks after sharp drawdowns
What surprised me
When I validated the rankings out-of-sample (2024\u20132025, using Alphalens to avoid look-ahead issues):\n* Operational and Flow edges provided most of the lift\n* Social edges (board interlocks) added much less than I expected\n* Graph features roughly doubled ranking quality versus price-only baselines\nThis wasn\u2019t obvious to me going in \u2014 I expected \u201csocial\u201d connections to matter more.
Why I\u2019m posting
I\u2019m in the process of turning this from a research notebook into a production dashboard, and before I lock in the graph schema I\u2019d love feedback from people who\u2019ve built large graphs in other domains.\nIn particular:\n* Have you seen board-interlock / social edges be predictive elsewhere?\n* Are there graph normalization tricks you\u2019ve found essential at this scale?\n* Any pitfalls you\u2019ve hit when mixing heterogeneous edge types?
Happy to answer questions about the graph construction, centrality calculations, or validation setup.","title":"Show HN:Built a 200k-edge market knowledge graph to filter false dip-buy signals","updated_at":"2026-03-05T23:14:55Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"rprend"},"title":{"matchLevel":"none","matchedWords":[],"value":"Open source, agentic knowledge bases for all of humanity's knowledge"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://alpharesearch.nyc/blog/launching-alpha-research/"}},"_tags":["story","author_rprend","story_47710058"],"author":"rprend","created_at":"2026-04-09T21:02:56Z","created_at_i":1775768576,"num_comments":0,"objectID":"47710058","points":3,"story_id":47710058,"title":"Open source, agentic knowledge bases for all of humanity's knowledge","updated_at":"2026-04-09T22:45:03Z","url":"https://alpharesearch.nyc/blog/launching-alpha-research/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"vortex_ape"},"title":{"matchLevel":"none","matchedWords":[],"value":"Finding Lookalikes of YC Companies"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://labs.alphalens.com/"}},"_tags":["story","author_vortex_ape","story_43025936"],"author":"vortex_ape","created_at":"2025-02-12T14:52:40Z","created_at_i":1739371960,"num_comments":0,"objectID":"43025936","points":1,"story_id":43025936,"title":"Finding Lookalikes of YC Companies","updated_at":"2025-02-12T14:53:29Z","url":"https://labs.alphalens.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tuando9627"},"title":{"matchLevel":"none","matchedWords":[],"value":"Edgar SEC filings search using NLP"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["alphasense"],"value":"https://alpharesearch.io/"}},"_tags":["story","author_tuando9627","story_31291644"],"author":"tuando9627","created_at":"2022-05-07T02:23:08Z","created_at_i":1651890188,"num_comments":0,"objectID":"31291644","points":1,"story_id":31291644,"title":"Edgar SEC filings search using NLP","updated_at":"2024-09-20T11:08:46Z","url":"https://alpharesearch.io/"}],"hitsPerPage":50,"nbHits":24,"nbPages":1,"page":0,"params":"query=AlphaSense&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":24,"processingTimingsMS":{"_request":{"roundTrip":17},"afterFetch":{"format":{"total":1}},"fetch":{"query":20,"scanning":1,"total":22},"total":24},"query":"AlphaSense","serverTimeMS":25}