| 1. | | Legal Contracts Built for AI Agents (paid.ai) |
| 72 points by arnon 10 days ago | 45 comments |
|
| 2. | | Getting good results from Claude Code (dzombak.com) |
| 490 points by ingve 71 days ago | 200 comments |
|
| 3. | | We revamped our docs for AI-driven development (freestyle.sh) |
| 90 points by benswerd 84 days ago | 35 comments |
|
| 4. | | About AI Evals (hamel.dev) |
| 189 points by TheIronYuppie 3 months ago | 43 comments |
|
| 5. | | Agentic Misalignment: How LLMs could be insider threats (anthropic.com) |
| 101 points by helloplanets 3 months ago | 84 comments |
|
| 6. | | Precision Clock Mk IV (mitxela.com) |
| 552 points by ahlCVA 4 months ago | 126 comments |
|
| 7. | | Claude's system prompt is over 24k tokens with tools (github.com/asgeirtj) |
| 627 points by mike210 5 months ago | 334 comments |
|
| 8. | | DeepSeek: Inference-Time Scaling for Generalist Reward Modeling (arxiv.org) |
| 163 points by tim_sw 6 months ago | 35 comments |
|
| 9. | | Understanding R1-Zero-Like Training: A Critical Perspective (github.com/sail-sg) |
| 160 points by pama 7 months ago | 21 comments |
|
| 10. | | New tools for building agents (openai.com) |
| 389 points by meetpateltech 7 months ago | 157 comments |
|
| 11. | | Ladder: Self-improving LLMs through recursive problem decomposition (arxiv.org) |
| 370 points by fofoz 7 months ago | 110 comments |
|
| 12. | | Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” (openpipe.ai) |
| 199 points by kcorbitt 7 months ago | 55 comments |
|
| 13. | | MIT 6.S184: Introduction to Flow Matching and Diffusion Models (csail.mit.edu) |
| 400 points by __rito__ 7 months ago | 24 comments |
|
| 14. | | ARC-AGI without pretraining (iliao2345.github.io) |
| 351 points by georgehill 7 months ago | 121 comments |
|
| 15. | | DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL (pretty-radio-b75.notion.site) |
| 322 points by sijuntan 8 months ago | 127 comments |
|
| 16. | | DeepSeek-R1 (github.com/deepseek-ai) |
| 1843 points by meetpateltech 9 months ago | 663 comments |
|
| 17. | | Things we learned about LLMs in 2024 (simonwillison.net) |
| 984 points by simonw 9 months ago | 582 comments |
|
| 18. | | Explaining Large Language Models Decisions Using Shapley Values (arxiv.org) |
| 89 points by veryluckyxyz 9 months ago | 19 comments |
|
| 19. | | Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com/paulpauls) |
| 579 points by PaulPauls 11 months ago | 99 comments |
|
| 20. | | Detecting when LLMs are uncertain (thariq.io) |
| 283 points by trq_ 11 months ago | 165 comments |
|
| 21. | | Bike Manufacturers Are Making Bikes Less Repairable (ifixit.com) |
| 207 points by LorenDB on Oct 14, 2024 | 206 comments |
|
| 22. | | Web scraping with GPT-4o: powerful but expensive (blancas.io) |
| 377 points by edublancas on Sept 2, 2024 | 167 comments |
|
| 23. | | Show HN: R2R V2 – A open source RAG engine with prod features (github.com/sciphi-ai) |
| 251 points by ocolegro on June 26, 2024 | 71 comments |
|
| 24. | | Cost of self hosting Llama-3 8B-Instruct (lytix.co) |
| 245 points by veryrealsid on June 14, 2024 | 183 comments |
|
| 25. | | Better RAG Results with Reciprocal Rank Fusion and Hybrid Search (assembled.com) |
| 249 points by johnjwang on May 30, 2024 | 57 comments |
|
| 26. | | Using Llamafiles for embeddings in local RAG applications (future.mozilla.org) |
| 141 points by tosh on May 16, 2024 | 23 comments |
|
| 27. | | Show HN: Hacker Search – A semantic search engine for Hacker News (hackersearch.net) |
| 233 points by jnnnthnn on May 2, 2024 | 73 comments |
|
| 28. | | Quantum mechanics is the operating system other physical theories run on (2007) (scottaaronson.com) |
| 101 points by cl3misch on April 17, 2024 | 88 comments |
|
| 29. | | Your LLM Is a Capable Regressor When Given In-Context Examples (arxiv.org) |
| 119 points by TaurenHunter on April 13, 2024 | 36 comments |
|
| 30. | | U.S. imposes first-ever national drinking water limits on PFAS (apnews.com) |
| 631 points by geox on April 10, 2024 | 427 comments |
|
|
| More |
