Tracked topic
… If you want recommendations for any Paper on Hugging Face checkout this Space You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @ librarian-bot recommend Cool paper - I liked the way "The Cold-Start Safety Gap in LLM Agents" frames the problem without making i… …
и как это г использовать This is an awful decision this is a shittiest one! clone repo : git clone https://user name:token@huggingface.co/xxxx · Thanks brother, you saved me hours of headaches :D passwordless authentication is more secure, in fact using token as password makes it "bruteforceless" t… …
… Cool, I like it. https://openai.com/index/hugging-face-model-evaluation-security-incident/
… These findings reveal that autonomous skill learning introduces a fundamentally new attack surface, highlighting the need for provenance tracking and security mechanisms throughout the entire skill lifecycle rather than only protecting runtime memory. …
… This comment has been hidden Does anybody know how can i set reasoning effort params in serving, for example, vllm? · If you use the Responses API hosted on HF https://router.huggingface.co/v1/responses , then you can do like this: from openai import OpenAI import os client = OpenAI base url= "http… …
… Uncovering the Security Debt of Autonomous Coding Agents 2026 Augmentation with Dilution: A Large-Scale Empirical Study of Human Contributor Ecosystems After AI Coding Agent Adoption 2026 Please give a thumbs up to this comment if you found it helpful! …