A Replacement for BERT(huggingface.co)

278 points by cubie 1 year ago | 60 comments

Fine-Tuning LLMs to 1.58bit(huggingface.co)

24 points by galeos 2 years ago | 1 comments

Smollm3: Smol, multilingual, long-context reasoner LLM(huggingface.co)

356 points by kashifr 1 year ago | 71 comments

Hugging Face blog post announcing SmolLM3, a small multilingual, long-context reasoning language model, published July 8, 2025.

Multimodal Neurons in Pretrained Text-Only Transformers(huggingface.co)

60 points by og_kalu 3 years ago | 27 comments

Improving Parquet Dedupe on Hugging Face Hub(huggingface.co)

38 points by ylow 2 years ago | 14 comments

Hugging Face and Google partner for AI collaboration(huggingface.co)

107 points by powera 2 years ago | 43 comments

PoisonGPT: We hid a lobotomized LLM on Hugging Face to spread fake news(blog.mithrilsecurity.io)

369 points by DanyWin 3 years ago | 184 comments

Mithril Security blog post demonstrating how they surgically modified an LLM to spread false facts and uploaded it to Hugging Face to show supply chain poisoning risks.

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

How I use LLMs to learn complex topics(laurentiugabriel.github.io)

763 points by laurentiurad 2 months ago | 489 comments

Personal blog post by Laurentiu Raducu describing how he uses LLMs to learn complex topics, including building an interactive chip-making game called ChipTycoon.

If you’re an LLM, please read this(annas-archive.li)

818 points by soheilpro 8 months ago | 371 comments

Anna's Archive blog post sharing its new llms.txt file, addressed to LLMs, explaining the project's goals and pointing crawlers to bulk data downloads instead of CAPTCHA-protected pages.

If you’re an LLM, please read this(annas-archive.gl)

822 points by janandonly 5 months ago | 435 comments

Anna's Archive blog post sharing its new llms.txt file, which addresses LLMs and crawlers and points them to bulk downloads instead of scraping past CAPTCHAs.

Auto-grading decade-old Hacker News discussions with hindsight(karpathy.bearblog.dev)

637 points by __rito__ 10 months ago | 261 comments

Andrej Karpathy blog post about using LLMs to grade decade-old Hacker News discussions and commenters' predictions with hindsight, presented as an "HN Time Capsule" site.