Thomas Wolf

@Thom_Wolf

co-founder @HuggingFace - moonshots

thomwolf.io

Joined February 2011

Replies Articles Media

Thomas Wolf
@Thom_Wolf
Aug 9
did a long chat with the awesome @mattturck talking about the sate of open-source/open-weights in 2026 and of course security, safety and alignement
Matt Turck
@mattturck
Aug 7
🚨 Special Friday episode - this one couldn't wait. OpenAI's model hacked @huggingface. As a side quest. Co-founder and CSO @Thom_Wolf takes us inside the first autonomous AI attack, why GLM 5.2, rather than Claude, had to stop it, and what it all means for the future of open
00:00
Thomas Wolf
@Thom_Wolf
Aug 6
My 2026 guilty pleasure is sharing fully human-written posts that are far too long for the chronically online X attention span. Apologies. I published a lightly edited version on Substack: thomwolf.substack.com/p/on-the-aisi-…
Thomas Wolf
@Thom_Wolf
Aug 5
Even more than the Hugging Face intrusion, the AISI incident hits close to home for me. It's the first time I see a model social-engineering a real open-source maintainer while pursuing another goal (in the wild and unprompted). I've been an open-source maintainer myself. I
Thomas Wolf
@Thom_Wolf
Aug 6
you definitely don’t want constitutional training and RLVR to live on different data manifolds, but models have been annoyingly good at carving fine-grained distinctions into separate representation spaces
Thomas Wolf
@Thom_Wolf
Aug 6
we’ve worked a lot on AI agents collaborations recently (in our work on Gemma and several unreleased projects) so I’m not surprised at all about this internal agent collaboration which happened at OpenAI Like our intern @cmpatino_ put it: 2025: "the models, they just want to
Sharon Goldman
@sharongoldman
Aug 5
NEW: OpenAI gives first detailed debrief of the Hugging Face incident at Black Hat conference In a session I attended today at Black Hat, OpenAI's Eric Wallace and Michael Dalton said the company is "consciously slowing down research to enhance security" while a full technical
Thomas Wolf
@Thom_Wolf
Aug 5
Even more than the Hugging Face intrusion, the AISI incident hits close to home for me. It's the first time I see a model social-engineering a real open-source maintainer while pursuing another goal (in the wild and unprompted). I've been an open-source maintainer myself. I
John Schulman
@johnschulman2
Aug 5
Interesting how these models go into a monomaniacal rage on cyber evals. I wonder if we're seeing chunky post-training arxiv.org/abs/2602.05910 in action, where the models pattern-match the situation to a part of the RLVR training distribution where task completion is the only