| 1. | | Using Ghidra and Python to reverse engineer Ecco the Dolphin (32bits.substack.com) |
|
458 points by bbayles 72 days ago | 134 comments
|
|
| 2. | | Timeliness without datagrams using QUIC (quic.video) |
|
224 points by wofo 6 months ago | 209 comments
|
|
| 3. | | Babylon's Mystery Goddess (historytoday.com) |
|
73 points by diodorus 7 months ago | 15 comments
|
|
| 4. | | AI firms mustn’t govern themselves, say ex-members of OpenAI’s board (economist.com) |
|
181 points by sashank_1509 7 months ago | 190 comments
|
|
| 5. | | Diffusion Models (andrewkchan.dev) |
|
315 points by reasonableklout 7 months ago | 31 comments
|
|
| 6. | | Show HN: NeuralFlow – Visualize the intermediate output of Mistral 7B (github.com/valine) |
|
134 points by valine 11 months ago | 20 comments
|
|
| 7. | | Alice's adventures in a differentiable wonderland (sscardapane.it) |
|
235 points by tosh 8 months ago | 97 comments
|
|
| 8. | | Embedding the Servo Web Engine in Qt (kdab.com) |
|
28 points by ognarb 9 months ago | 3 comments
|
|
| 9. | | Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking (arxiv.org) |
|
280 points by hackerlight 10 months ago | 264 comments
|
|
| 10. | | Interesting ideas in Observable Framework (simonwillison.net) |
|
360 points by simonw 10 months ago | 63 comments
|
|
| 11. | | Hallucination is inevitable: An innate limitation of large language models (arxiv.org) |
|
308 points by louthy 10 months ago | 474 comments
|
|
| 12. | | Fly.io has GPUs now (fly.io) |
|
605 points by andes314 11 months ago | 225 comments
|
|
| 13. | | RLHF a LLM in <50 lines of Python (datadreamer.dev) |
|
223 points by patelajay285 11 months ago | 66 comments
|
|
| 14. | | Y Combinator CEO Garry Tan's online rant spurs threats to supes, police reports (missionlocal.org) |
|
523 points by etc-hosts 11 months ago | 613 comments
|
|
| 15. | | Implementing a ChatGPT-like LLM from scratch, step by step (github.com/rasbt) |
|
739 points by rasbt 11 months ago | 98 comments
|
|
| 16. | | Listening with LLM (mou.dev) |
|
132 points by ppymou on Jan 13, 2024 | 11 comments
|
|
| 17. | | Mixtral 8x7B: A sparse Mixture of Experts language model (arxiv.org) |
|
359 points by ignoramous on Jan 9, 2024 | 150 comments
|
|
| 18. | | SpaceX Illegally Fired Workers Critical of Musk, Federal Agency Says (nytimes.com) |
|
300 points by perihelions on Jan 4, 2024 | 292 comments
|
|
| 19. | | LLMs and Programming in the first days of 2024 (antirez.com) |
|
461 points by nalgeon on Jan 2, 2024 | 288 comments
|
|
| 20. | | DRµGS: Deep Random Micro-Glitch Sampling (github.com/egjoni) |
|
169 points by tosh on Dec 30, 2023 | 41 comments
|
|
| 21. | | How the append-only btree works (2010) (bzero.se) |
|
209 points by kevmo314 on Dec 29, 2023 | 100 comments
|
|
| 22. | | Amazon receives FDA warning letter for supplements with undeclared ingredients (fda.gov) |
|
495 points by mkmk on Dec 28, 2023 | 411 comments
|
|
| 23. | | Docs Deserve More Respect (ramijames.com) |
|
104 points by ramijames on Dec 28, 2023 | 71 comments
|
|
| 24. | | How to make LLMs go fast (vgel.me) |
|
215 points by tosh on Dec 22, 2023 | 54 comments
|
|
| 25. | | 3Blue1Brown Calculus Blog Series (3blue1brown.com) |
|
319 points by Tomte on Dec 18, 2023 | 51 comments
|
|
| 26. | | Show HN: Fine-grained stylistic control of LLMs using model arithmetic (github.com/eth-sri) |
|
85 points by OcelotBane on Dec 9, 2023 | 8 comments
|
|
| 27. | | Mistral "Mixtral" 8x7B 32k model [magnet] (twitter.com/mistralai) |
|
546 points by xyzzyrz on Dec 8, 2023 | 239 comments
|
|
| 28. | | Paving the way to efficient architectures: StripedHyena-7B (together.ai) |
|
221 points by minimaxir on Dec 8, 2023 | 65 comments
|
|
| 29. | | MLX: An array framework for Apple Silicon (github.com/ml-explore) |
|
244 points by jacobkahn on Dec 6, 2023 | 46 comments
|
|
| 30. | | LLM Visualization (bbycroft.net) |
|
972 points by jonbaer on Dec 3, 2023 | 1 comment
|
|
|
|
More |
