METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.

I'll be at #ACL2026 in San Diego, presenting our recent works spanning AI safety! 📍 Poster (Jul 6) Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models arxiv.org/abs/2601.15220 (1/2)

It's interesting how the usage of LLMs has been quickly progressing to higher levels of abstraction: 1. prompt engineering 2. context engineering 3. agent scaffold engineering (we are here now) 4. multi-agent architecture engineering 5. ??? It's also curious how people don't discuss the previous stages that much anymore. Like, no one discusses prompt engineering now, and discussions around context engineering are becoming less frequent.

🚨 Fine-tuning your model to be more helpful or empathetic might be making it less private, without you noticing. In our latest work, we show that benign fine-tuning can silently break contextual privacy in language models while safety & general capabilities appear intact. ⬇️

🚨 New paper alert: Our recent work on LLM safety has been accepted to ICLR 2025 🇸🇬 We propose a new framework for LLMs safety. 🧵 (1/7) #LLM #AISafety #ICLR2025 #Certification #AdversarialRobustness #NLP #Shhhhhh #DomainCertification #AI