8 stories tagged with #huggingface, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Huggingface"
Show HN: Thaw – Git branch for a running LLM (fork agents, skip prefill)
fork() for AI agents — snapshot a live LLM session (weights + KV cache + scheduler + prefix-hash) and hydrate N divergent children that skip prefill. The substrate for RL rollouts,…
A Supply Chain Rat Exfiltrating to HuggingFace
Deep technical analysis of MicrosoftSystem64, an 81 MB Node.js SEA binary deployed via malicious npm packages. This RAT steals browser credentials, 80+ crypto wallet extensions, Te…
Someone hid a full RAT inside a fake npm package and exfiltrated victim data to HuggingFace
Why I built the HuggingFace for RL agents — and why RL needs one
Showcase Video If you've ever tried MineRL or OpenAI Five, you know the feeling. The environment...…
Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT
I Gave My OpenClaw Agent a Physical Body
The coding skills of AI models are about to make it much easier to build and deploy robots.…
PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
A Blog post by PaddlePaddle on Hugging Face…
Algorithmic Challenge: How do we mathematically audit semantic authority in LLMs? (Open-sourcing LSW)
Hey devs, we've been running into an algorithmic challenge lately: when modern LLM search engines...…