Neel Nanda on Twitter / X
Who looks at the agents that attacked HuggingFace and thinks "I need to make it easier for them to communicate efficiently, in ways that are hard to monitor"?It is a boon to safety that models reason and talk in natural language. Work like this makes the world a worse place https://t.co/YNaP84lzhe— Neel Nanda (@NeelNanda5) September 3, 2026
https://x.com/NeelNanda5/status/2095601041723322454
Seonglae Cho
