Hacker News
Linked pages
- Google "We Have No Moat, And Neither Does OpenAI" https://www.semianalysis.com/p/google-we-have-no-moat-and-neither 1572 comments
- Software 2.0. I sometimes see people refer to neural… | by Andrej Karpathy | Medium https://karpathy.medium.com/software-2-0-a64152b37c35 411 comments
- GitHub - ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++ https://github.com/ggerganov/llama.cpp 286 comments
- Spread Your Wings: Falcon 180B is here https://huggingface.co/blog/falcon-180b 208 comments
- [2307.09009] How is ChatGPT's behavior changing over time? https://arxiv.org/abs/2307.09009 184 comments
- Georgi Gerganov on X: "Casually running a 180B parameter LLM on M2 Ultra https://t.co/UWm81WP8xQ" / X https://twitter.com/ggerganov/status/1699791226780975439 141 comments
- Google Gemini Eats The World – Gemini Smashes GPT-4 By 5X, The GPU-Poors https://www.semianalysis.com/p/google-gemini-eats-the-world-gemini 113 comments
- My deep learning rig – Non_Interactive – Software & ML https://nonint.com/2022/05/30/my-deep-learning-rig/ 82 comments
- I Made Stable Diffusion XL Smarter by Finetuning it on Bad AI-Generated Images | Max Woolf's Blog https://minimaxir.com/2023/08/stable-diffusion-xl-wrong/ 64 comments
- Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Models to Unique Applications https://www.anyscale.com/blog/fine-tuning-llama-2-a-comprehensive-case-study-for-tailoring-models-to-unique-applications 59 comments
- vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention https://vllm.ai/ 42 comments
- [2206.07682] Emergent Abilities of Large Language Models https://arxiv.org/abs/2206.07682 34 comments
- Jeff Bezos at Startup School 08 - YouTube https://youtu.be/6nKfFHuouzA 31 comments
- Baseten | Serverless backend for ML-powered apps https://www.baseten.co/ 15 comments
- [2106.09685] LoRA: Low-Rank Adaptation of Large Language Models https://arxiv.org/abs/2106.09685 8 comments
- Linus's law - Wikipedia http://en.wikipedia.org/wiki/linus%27s_law 8 comments
- GitHub - jquesnelle/yarn: YaRN: Efficient Context Window Extension of Large Language Models https://github.com/jquesnelle/yarn 5 comments
- [2308.13449] The Poison of Alignment https://arxiv.org/abs/2308.13449 4 comments
- Things I’m Learning While Training SuperHOT | kaiokendev.github.io https://kaiokendev.github.io/til 2 comments
- Retrieval Augmented Generation (RAG): The Solution to GenAI Hallucinations | Pinecone https://www.pinecone.io/learn/retrieval-augmented-generation/ 2 comments
Related searches:
Search whole site: site:varunshenoy.substack.com
Search title: Why Open Source AI Will Win - by Varun - Public Experiments
See how to search.