Yarin
@yaringal
Followers
41K
Following
5K
Media
156
Statuses
2K
Professor of Machine Learning, University of Oxford @OATML_Oxford Group Leader Director of Research at the UK govt's AI Security Institute (AISI)
Oxford, England
Joined February 2014
RT @StephenLCasper: Thanks to collaborators! @AISecurityInst , @AiEleuther, Kyle O’Brien, @StephenLCasper, @QuentinAnthon15, @tomekkorbak,….
0
1
0
RT @BlancheMinerva: It was a joy to work with @AISecurityInst and all of my wonderful co-authors on this project: Kyle O’Brien, @StephenLCa….
0
1
0
RT @_robertkirk: Very excited for this work to be out. We do large-scale empirical experiments on data filtering for harmful knowledge, an….
0
4
0
RT @StephenLCasper: 🧵 New paper from @AISecurityInst x @AiEleuther that I led with Kyle O’Brien:. Open-weight LLM safety is both important….
0
39
0
RT @alxndrdavies: We at @AISecurityInst worked with @OpenAI to test GPT-5's safeguards. We identified multiple jailbreaks, including a univ….
0
24
0
RT @soundboy: I am keen to see more work on AI security that starts from a "open-first" perspective as @BlancheMinerva puts it. Great to se….
0
9
0
RT @alxndrdavies: We at @AISecurityInst worked with @OpenAI to test & improve Agent’s safeguards prior to release. A few notes on our exper….
0
29
0
RT @iliaishacked: My friends, I want to organise Secure AI Club in London -- gig for people interested in (practical!) AI Security. Not jus….
docs.google.com
I want to organise a Secure AI Club meetup in London Need to figure out how many people will come to find appropriate venue
0
16
0
RT @edwardfhughes: Self-improvement (cf DeepSeek, o3, Gemini Thinking) is the process of turning unknown knowns into known knowns. True op….
0
23
0
RT @matthewclifford: Really delighted with the outcome of the Spending Review: £2bn to support the AI Opportunities Action Plan, including….
0
39
0
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
6
2
24
RT @GaryMarcus: ⚠️ This is insane — and not in a good way. Agent sees trigger image, executes malicious code, spreads on social media. To….
0
37
0
RT @KyleCranmer: Thanks @kjw_chiu for linking to this satisfying article, which confirms my mental model for what is going on, and also res….
0
22
0
RT @vasumanmoza: Claude 4 just refactored my entire codebase in one call. 25 tool invocations. 3,000+ new lines. 12 brand new files. It m….
0
3K
0
RT @schwabpa: @yaringal @OATML_Oxford Nice chance to work on some of the most exciting problems of our time!.
0
1
0