Congratulations to charig yang who won best presentation and @jacksonmattt @shreshthmalik for best poster at the Joint CDT student conference with Bristol, Lincoln and Edinburgh CDTs Autonomous Intelligent Machines & Systems @Oxford University of Oxford

Tricky alien worlds easier to find when humans and machines team up trib.al/pfixDcV

Today, we’re starting a blog post sequence explaining how causality underpins many critical aspects of safe AGI, including agency, incentives, misspecification, generalisation, fairness, and corrigibility. We explain past work and open questions. tinyurl.com/caus-safe-agi

A colleague called my attention to Tom Everitt's "Towards Causal Foundations of Safe AGI" alignmentforum.org/s/pcdHisDEGLbx… alignmentforum.org/posts/Qi77Tu3e…. A good read!

Excited to be working on "things moving in space" with FDL.AI NASA this summer #explainitlikeim5 #FDLX #helio

at #icml today? come chat with us about a new method to sample batches for active learning! SPGIM: spigmworkshop.github.io Poster Session: 12-1pm and 4-5pm 📄 arxiv.org/abs/2306.15058 with Shreshth Malik Salem Lahlou Moksh Jain Kolya Malkin Tristan Deleu Yoshua Bengio Yarin

Fully Funded 4-year Doctoral Studentship Joint with Five AI and the EPSRC CDT in Autonomous Intelligent Machines & Systems (AIMS) - Starting October 2023. Further details can be found here: aims.robots.ox.ac.uk/study/industry…

Happy to share that I'll be helping the UK taskforce as director of research (together with David Krueger). We're heavily recruiting - if you have technical expertise and want to work on Frontier Models (LLMs, generative AI), please read here x.com/soundboy/statu…

FDL-X was a resounding success with compelling results for each team and an integrated ML pipeline that we can't wait to show off 🚀 Tune in to FDL-X live on 9/20 for a live broadcast of this year's results docs.google.com/forms/d/e/1FAI…

Excited to share our new work! 📚arxiv.org/abs/2310.16410 Most interpretability research focuses on understanding which human concepts AI systems encode. We ask a different question: Do AI systems encode superhuman concepts, and can we use them to further human knowledge?🧵(1/12)

We’re organising a virtual open day! 📅 4-5:30 PM GMT on 22 Nov 2023 Anyone interested in joining OATML_Oxford 🥣🌾for a PhD is welcome! Come to meet OATMLers, get a feel for our group, and ask any questions you may have! ✏️ Sign Up: forms.gle/MSMwp3wvUR9Cnc…

Out in Science today: In our paper, we describe extreme AI risks and concrete actions to manage them, including tech R&D and governance. “For AI to be a boon, we must reorient; pushing AI capabilities alone is not enough.”

We're looking for 2 postdocs to join OATML_Oxford, working on Foundational AI Safety. You’ll lead and contribute to projects aimed at developing principled and practical safe AI methods which would be used in real systems eg in the medical domain. Closing date 12th June Links>>

Is your LLM hallucinating? 👻 Our nature paper shows how to detect when an LLM is making things up. A 'confabulating' LLM answers with inconsistent meanings when re-asked the same question. We use this to estimate uncertainty and detect confabulations. Learn more 🧵👇 1/

After thousands of microscope hours and several years of painstaking optimisation, Callie Glynn and I are very excited to share our latest manuscript. We outline our approach to investigate the molecular organisation within hippocampus tissue using cryo-ET.

⚠️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] 🧵

I'm at #ICCV2025 and will be giving a keynote talk tomorrow at the SaFeMM-AI Workshop @ ICCV25 workshop at 10:55 (room 308 B) Drop by to say hi! I'm also looking for PhD students and postdocs to join OATML_Oxford - happy to chat during the conference. Email: [email protected]

Reminder - PhD applications for OATML are now open The first funding deadline is December 2 - candidates interested in developing Bayesian deep learning methodology, applications of ML, AI security, and understanding ML methodology are encouraged to apply More info: