Hacker News · AI·1d agoA single function Jev-like wrapper for LLMs, including vision models#logprobs#vision-llm#jev 9 min
Hugging Face daily papers·6d agoEDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation#tool-calling#synthetic-data#agents1
Hugging Face daily papers·10d agoWhen EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation#distillation#eos-tokens#gemma
arXiv cs.CR·15d agoEvaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks#agentic-ai#context-engineering#ctfAI safety & security1
arXiv cs.AI / cs.LG / cs.CL·16d agoFrom Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge#gemma#hidden-states#interpretabilityAI research1
arXiv cs.AI / cs.LG / cs.CL·18d agoSAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?#ai-agents#benchmark#evalsAI research2
Hugging Face daily papers·19d agoSAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?#ai-agents#benchmark#evals1
Hugging Face daily papers·19d agoCo-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails#agentic-ai#ai-agents#fine-tuning1
Google · AI·25d agoThe latest AI news we announced in August 2026#gemini#gemini-3-5-transcribe#gemini-3-7-flash 5 min