Hackernews posts about Llama 3

Llama 3 is an AI-powered chatbot that uses pure NumPy to generate human-like conversations in a browser-based interface.

1. DeepDive in everything of Llama3: revealing detailed insights and implementation (github.com)
   191 points by therealoliver about 24 hours ago | 12 comments
2. Implementing LLaMA3 in 100 Lines of Pure Jax (saurabhalone.com)
   162 points by jxmorris12 4 days ago | 22 comments
3. FSF: Llama 3.1 Community License is not a Free Software license (www.fsf.org)
   5 points by pabs3 27 days ago | 1 comments
4. Distilled DeepSeek R1 Outperforms Llama 3 and GPT-4o in Classifying Error Logs (rootly.com)
   2 points by sylvainkalache 3 days ago | discuss
5. Llama3.2 vision model and nosiy images
   1 points by epop 6 days ago | discuss
6. Tell HN: Llama 3 commented "why" on my code
   1 points by UCdallasGA 18 days ago | discuss
7. FSF: 'Llama 3.1 Community License is not a free software license' (www.fsf.org)
   1 points by MilnerRoute 27 days ago | discuss
8. AllenAI Tulu 3 405B available for chat and download
   12 points by soundworlds 18 days ago | discuss
9. Show HN: Chrome extension to run DeepSeek, LLMs and Whisper locally in browser (github.com)
   10 points by tantara 20 days ago | 2 comments
10. Free AI API Key
    5 points by singularis 29 days ago | 5 comments
11. Show HN: Focu, open-source mindful productivity app for macOS (github.com)
    5 points by martin-buur 12 days ago | discuss
12. Show HN: Distill your own model from DeepSeek R1 in 30 mins (open+GUI)
    4 points by scosman 16 days ago | discuss
13. Show HN: Chrome extension to run GenAI models in browser (github.com)
    4 points by tantara 20 days ago | discuss
14. Fact-checking DeepSeek hype with DeepSeek
    4 points by omega3 24 days ago | discuss
15. Show HN: Nominate – a macOS app that renames PDFs based on their contents (github.com)
    3 points by _mattt 17 days ago | discuss
16. Show HN: MakerTime – Measure Deep Work via screen activity fed into an LLM (www.makertime.ai)
    2 points by tleyden5iwx 30 days ago | discuss
17. 83% skip agreements, 61% get "ripped off". AI – risk analysis, would you use?
    1 points by zane12580 4 days ago | 2 comments
18. Show HN: Quickly submit links to HN from any app on your Android device (play.google.com)
    1 points by LorenDB 27 days ago | 2 comments
19. Show HN: Codedd – automating software auditing for investment rounds (www.codedd.ai)
    1 points by cpachmann 10 days ago | discuss
20. Selene Mini: Open-sourced SOTA small language-model-as-a-judge (huggingface.co)
    20 points by kaikaidai 24 days ago | 4 comments
21. K8s vs. DeepSeek: When Production Chaos Met AI Promises (komodor.com)
    7 points by itielshwartz 12 days ago | 2 comments
22. DeepHermes 3: unify reasoning and intuitive language model capabilities (huggingface.co)
    1 points by TheJCDenton 7 days ago | discuss
23. Show HN: I Wrote an Open-Source Alternative to OpenAI Operator – For Any LLM (github.com)
    15 points by MagMueller 30 days ago | 3 comments
24. Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill (github.com)
    14 points by sssummer 12 days ago | discuss
25. Show HN: Meetily – Open-Source AI Meeting Assistant (Alt to Otter.ai)
    3 points by zackriya about 8 hours ago | 2 comments
26. Show HN: Bodhi App – Local LLM Inference (getbodhi.app)
    1 points by anagri 16 days ago | discuss
27. Ask HN: How to get around or remove censorship in Deepseek-R1?
    5 points by jimmydoe 26 days ago | 1 comments
28. Show HN: Open-source application to run local LLM easily (kolosal.ai)
    4 points by rifkybujana 19 days ago | 2 comments
29. Show HN: DocEditor – LLM Open Source Document Editor (Streamlit Live Demo) (github.com)
    1 points by doc-editor 6 days ago | 1 comments
30. Meta Llama 3 (llama.meta.com)
    2199 points by bratao 10 months ago | 923 comments
31. Llama3 implemented from scratch (github.com)
    1041 points by Hadi7546 9 months ago | 269 comments
32. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models (ai.meta.com)
    924 points by nmwnmw 5 months ago | 328 comments
33. Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com)
    579 points by PaulPauls 3 months ago | 99 comments
34. Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU (github.com)
    547 points by abi 10 months ago | 139 comments
35. Llama 3 implemented in pure NumPy (docs.likejazz.com)
    476 points by orixilus 9 months ago | 50 comments
36. Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars (aksh-garg.medium.com)
    459 points by minimaxir 9 months ago | 77 comments
37. Llama 3.1 (llama.meta.com)
    437 points by luiscosio 7 months ago | 269 comments
38. Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (cerebras.ai)
    427 points by benchmarkist 3 months ago | 156 comments
39. Llama-3.3-70B-Instruct (huggingface.co)
    425 points by pr337h4m 3 months ago | 219 comments
40. g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains (github.com)
    334 points by gfortaine 5 months ago | 148 comments
41. Llama 3.1 Omni Model (github.com)
    304 points by taikon 5 months ago | 41 comments
42. Cost of self hosting Llama-3 8B-Instruct (blog.lytix.co)
    245 points by veryrealsid 8 months ago | 183 comments
43. I Self-Hosted Llama 3.2 with Coolify on My Home Server (geek.sg)
    221 points by whitefables 4 months ago | 90 comments
44. llama-fs: A self-organizing file system with llama 3 (github.com)
    221 points by archb 9 months ago | 62 comments
45. Llama 3.1 in C (github.com)
    212 points by AMICABoard 7 months ago | 36 comments
46. Run llama3 locally with 1M token context (ollama.com)
    204 points by mritchie712 10 months ago | 72 comments
47. Show HN: Llama 3.3 70B Sparse Autoencoders with API access (www.goodfire.ai)
    201 points by trq_ 2 months ago | 51 comments
48. Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B (github.com)
    192 points by ashvardanian 10 months ago | 64 comments
49. Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com)
    189 points by felarof 5 months ago | 52 comments
50. Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally (ollama.com)
    182 points by BUFU 4 months ago | 25 comments
51. Llama 3 8B is almost as good as Wizard 2 8x22B (huggingface.co)
    168 points by tosh 10 months ago | 111 comments
52. Longwriter – Increase llama3.1 output to 10k words (github.com)
    154 points by taikon 5 months ago | 29 comments
53. Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai)
    147 points by campers 4 months ago | 84 comments
54. Hermes 3: The First Fine-Tuned Llama 3.1 405B Model (lambdalabs.com)
    146 points by mkaic 6 months ago | 67 comments
55. Fine tune LLAMA3 on million scale dataset in consumer GPU using QLora, DeepSpeed (medium.com)
    145 points by mehulashah 10 months ago | 26 comments
56. Llama 3 feels significantly less censored than its predecessor (ollama.com)
    123 points by davidbarker 10 months ago | 39 comments
57. Mark Zuckerberg: Llama 3, $10B Models, Caesar Augustus, Bioweapons [video] (www.youtube.com)
    107 points by tosh 10 months ago | 42 comments
58. Has Llama-3 just killed proprietary AI models? (www.kadoa.com)
    103 points by hubraumhugo 10 months ago | 70 comments
59. Accessing Math Solutions via Monte Carlo Self-Refine with LLaMa-3 8B (arxiv.org)
    100 points by belter 9 months ago | 9 comments