🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Thanks Ken Chiu for linking to this satisfying article, which confirms my mental model for what is going on, and also resolves some of my own concerns with that explanation. physics.stackexchange.com/questions/1110…

Self-improvement (cf DeepSeek, o3, Gemini Thinking) is the process of turning unknown knowns into known knowns. True open-endedness (cf AlphaGo Move 37, automation of science) is the process of turning unknown unknowns into known knowns.

This is a great opportunity to join a really strong team - I've been working with this team very closely over the past year and a half, and would highly recommend the opportunity to join. Please share with people for whom you reckon this might be useful!

Fundamental Limitations in Defending LLM Finetuning APIs Xander Davies (Xander Davies), Eric Winsor, Tomek Korbak, Alexandra Souly (Alexandra Souly), Robert Kirk (Robert Kirk), Christian Schroeder de Witt (Christian Schroeder de Witt), Yarin

⚠️Beware: Your AI assistant could be hijacked just by encountering a malicious image online! Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵

Hot take: I think we just demonstrated the first AI agent computer worm 🤔 When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents This is a chance to talk about agent security 👇

We have a senior postdoc position available with OATML_Oxford (closing 19/05) to lead work on LLM based causal reasoning with GSK. Please share with anyone you think this might be relevant to! my.corehr.com/pls/uoxrecruit…

I will be at ICLR if anyone wants to chat about this / other opportunities with the group. DM me

Thrilled to share that I’ve joined the OATML_Oxford as a postdoc, working with Yarin! Excited to dive deeper into machine learning research with such an inspiring team. 👋 DMs open – happy to connect, chat, and collaborate!

🚨 We’re hiring! Our group OATML_Oxford is looking for a senior postdoc to work on LLM-based causal reasoning. Yarin will be at ICLR – feel free to reach out and chat with him about the opportunity! 🔍📩 Please share with anyone you think this might be relevant to!

Yarin OATML_Oxford Nice chance to work on some of the most exciting problems of our time!

Claude 4 just refactored my entire codebase in one call. 25 tool invocations. 3,000+ new lines. 12 brand new files. It modularized everything. Broke up monoliths. Cleaned up spaghetti. None of it worked. But boy was it beautiful.

Veo 3 lands in the UK and is now also available on the Gemini app. Sound on!

I think it's quite misleading for the big labs to be promoting how well their VLMs work on pokemon, given how much (game-specific) manual annotation is required behind the scenes. Solving general tasks from pixel input is much harder than coding ("Moravec's revenge").

⚠️ This is insane — and not in a good way. Agent sees trigger image, executes malicious code, spreads on social media. Totally new kind of computer worm. 😱

Funding opportunity with the UK's AI security institute! I will be hosting the next online webinar to give an overview of the opportunity - please join! aisi.gov.uk/work/new-updat…

Evaluating forgetting is hard. We show where existing tools fall short, especially when they accidentally influence the very thing they're testing arxiv.org/pdf/2506.00688 Zhili Feng YixuanEvenXu Alex Robey Robert Kirk Xander Davies Yarin and Zico Kolter

Really delighted with the outcome of the Spending Review: £2bn to support the AI Opportunities Action Plan, including £500m for SovereignAI. So much to do but this gives the UK a great foundation.

My friends, I want to organise Secure AI Club in London -- gig for people interested in (practical!) AI Security. Not just academic toy setups, but actually making systems reliable. Trying to gauge interest, please sign up here: forms.gle/zSUMh6ykthQwtt…

We at AI Security Institute worked with OpenAI to test & improve Agent’s safeguards prior to release. A few notes on our experience🧵 1/4