| 1. | | Understanding R1-Zero-Like Training: A Critical Perspective (github.com/sail-sg) |
|
157 points by pama 2 days ago | 21 comments
|
|
| 2. | | New tools for building agents (openai.com) |
|
389 points by meetpateltech 13 days ago | 157 comments
|
|
| 3. | | Ladder: Self-improving LLMs through recursive problem decomposition (arxiv.org) |
|
370 points by fofoz 17 days ago | 110 comments
|
|
| 4. | | Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” (openpipe.ai) |
|
199 points by kcorbitt 18 days ago | 55 comments
|
|
| 5. | | MIT 6.S184: Introduction to Flow Matching and Diffusion Models (csail.mit.edu) |
|
400 points by __rito__ 22 days ago | 24 comments
|
|
| 6. | | ARC-AGI without pretraining (iliao2345.github.io) |
|
351 points by georgehill 20 days ago | 121 comments
|
|
| 7. | | DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL (pretty-radio-b75.notion.site) |
|
322 points by sijuntan 41 days ago | 127 comments
|
|
| 8. | | DeepSeek-R1 (github.com/deepseek-ai) |
|
1843 points by meetpateltech 63 days ago | 663 comments
|
|
| 9. | | Things we learned about LLMs in 2024 (simonwillison.net) |
|
984 points by simonw 83 days ago | 582 comments
|
|
| 10. | | Explaining Large Language Models Decisions Using Shapley Values (arxiv.org) |
|
89 points by veryluckyxyz 87 days ago | 19 comments
|
|
| 11. | | Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com/paulpauls) |
|
579 points by PaulPauls 4 months ago | 99 comments
|
|
| 12. | | Detecting when LLMs are uncertain (thariq.io) |
|
283 points by trq_ 5 months ago | 165 comments
|
|
| 13. | | Bike Manufacturers Are Making Bikes Less Repairable (ifixit.com) |
|
207 points by LorenDB 5 months ago | 206 comments
|
|
| 14. | | Web scraping with GPT-4o: powerful but expensive (blancas.io) |
|
377 points by edublancas 6 months ago | 167 comments
|
|
| 15. | | Show HN: R2R V2 – A open source RAG engine with prod features (github.com/sciphi-ai) |
|
251 points by ocolegro 9 months ago | 71 comments
|
|
| 16. | | Cost of self hosting Llama-3 8B-Instruct (lytix.co) |
|
245 points by veryrealsid 9 months ago | 183 comments
|
|
| 17. | | Better RAG Results with Reciprocal Rank Fusion and Hybrid Search (assembled.com) |
|
249 points by johnjwang 9 months ago | 57 comments
|
|
| 18. | | Using Llamafiles for embeddings in local RAG applications (future.mozilla.org) |
|
141 points by tosh 10 months ago | 23 comments
|
|
| 19. | | Show HN: Hacker Search – A semantic search engine for Hacker News (hackersearch.net) |
|
233 points by jnnnthnn 10 months ago | 73 comments
|
|
| 20. | | Quantum mechanics is the operating system other physical theories run on (2007) (scottaaronson.com) |
|
101 points by cl3misch 11 months ago | 88 comments
|
|
| 21. | | Your LLM Is a Capable Regressor When Given In-Context Examples (arxiv.org) |
|
119 points by TaurenHunter 11 months ago | 36 comments
|
|
| 22. | | U.S. imposes first-ever national drinking water limits on PFAS (apnews.com) |
|
631 points by geox 11 months ago | 427 comments
|
|
| 23. | | Chronon, Airbnb's ML feature platform, is now open source (medium.com/airbnb-engineering) |
|
224 points by vquemener 11 months ago | 112 comments
|
|
| 24. | | Storybook 8 (storybook.js.org) |
|
86 points by unleashit on March 13, 2024 | 36 comments
|
|
| 25. | | LLM Visualization (bbycroft.net) |
|
1592 points by plibither8 on Dec 3, 2023 | 131 comments
|
|
| 26. | | Forecasts need to have error bars (andrewpwheeler.com) |
|
334 points by apwheele on Dec 4, 2023 | 159 comments
|
|
| 27. | | Causal inference as a blind spot of data scientists (dzidas.com) |
|
225 points by Dzidas on Oct 15, 2023 | 102 comments
|
|
| 28. | | Inverted Transformers Are Effective for Time Series Forecasting (arxiv.org) |
|
206 points by beefman on Oct 11, 2023 | 38 comments
|
|
| 29. | | QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org) |
|
315 points by Garcia98 on May 24, 2023 | 107 comments
|
|
| 30. | | Facing sky-high connection fees, rural Ontarians go off the grid (cbc.ca) |
|
317 points by dgudkov on Oct 26, 2021 | 388 comments
|
|
|
|
More |
