Hacker News new | past | comments | ask | show | jobs | submit | _giorgio_'s favorites login
1. Deterioration of local community a major driver of loss of play-based childhood (afterbabel.com)
402 points by throwup238 3 days ago | 451 comments
2. Let's reproduce GPT-2 (124M) [video] (youtube.com)
44 points by thebuilderjr 4 days ago | 4 comments
3. Show HN: We've open-sourced our LLM attention visualization library (github.com/labmlai)
194 points by lakshith-403 4 days ago | 15 comments
4. σ-GPTs: A new approach to autoregressive models (arxiv.org)
293 points by mehulashah 6 days ago | 93 comments
5. Geometry for Entertainment (1950) (archive.org)
178 points by the-mitr 14 days ago | 46 comments
6. New attention mechanisms that outperform standard multi-head attention (arxiv.org)
233 points by snats 15 days ago | 49 comments
7. Ex-OpenAI board member reveals what led to Sam Altman's brief ousting (businessinsider.com)
785 points by blackmanta 16 days ago | 805 comments
8. Mistral Fine-Tune (github.com/mistralai)
191 points by alexmolas 19 days ago | 62 comments
9. Financial Statement Analysis with Large Language Models (ssrn.com)
573 points by mellosouls 20 days ago | 208 comments
10. Bento3D (polar-tadpole-97b.notion.site)
238 points by sdenton4 24 days ago | 74 comments
11. Llama3 implemented from scratch (github.com/naklecha)
1041 points by Hadi7546 25 days ago | 269 comments
12. Show HN: I built a website to create financial models for any stock online (useequityval.com)
287 points by trevzercap 27 days ago | 150 comments
13. Llama 3 implemented in pure NumPy (likejazz.com)
476 points by orixilus 28 days ago | 50 comments
14. LoRA+: Efficient Low Rank Adaptation of Large Models (arxiv.org)
181 points by veryluckyxyz 46 days ago | 47 comments
15. Watch cars evolve using genetic algorithm (rednuht.org)
484 points by memalign 47 days ago | 73 comments
16. Fragmented thinking is a bigger threat to flow state than interruptions (stackblitz.com)
386 points by nickwritesit 49 days ago | 163 comments
17. The Princeton Companion to Applied Mathematics (nhigham.com)
215 points by teleforce 46 days ago | 34 comments
18. Immersive Linear Algebra (2015) (immersivemath.com)
876 points by oumua_don17 33 days ago | 71 comments
19. Phytomining – Extracting Minerals via Plants (energy.gov)
127 points by Gaishan 67 days ago | 53 comments
20. OpenVoice: Instant Voice Cloning (github.com/myshell-ai)
270 points by tosh 48 days ago | 154 comments
21. I rewired my brain to become fluent in math (2014) (nautil.us)
406 points by ColinWright 48 days ago | 199 comments
22. Better and Faster Large Language Models via Multi-Token Prediction (arxiv.org)
302 points by jasondavies 43 days ago | 128 comments
23. Raspberry Pi Connect (raspberrypi.com)
199 points by vquemener 37 days ago | 78 comments
24. CS388: Natural Language Processing (utexas.edu)
178 points by gone35 35 days ago | 10 comments
25. Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x (hao-ai-lab.github.io)
461 points by zhisbug 36 days ago | 98 comments
26. TimesFM: Time Series Foundation Model for time-series forecasting (github.com/google-research)
317 points by yeldarb 36 days ago | 118 comments
27. Tokens, n-grams, and bag-of-words models (2023) (zilliz.com)
160 points by fzliu 70 days ago | 16 comments
28. Let's Think Dot by Dot: Hidden Computation in Transformer Language Models (arxiv.org)
159 points by Jimmc414 47 days ago | 32 comments
29. What can LLMs never do? (strangeloopcanon.com)
460 points by henrik_w 47 days ago | 374 comments
30. The formation and revision of intuitions (2023) [pdf] (columbia.edu)
53 points by luu 47 days ago | 8 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: