Grad student trying to understand the history of humanity, the future of AI, and how to make both of these things work together in the present.
Joined June 2025
- Tweets 23
- Following 6
- Followers 44
- Likes 39
6 Photos and videos
Super excited to have been part of preparing and delivering teaching materials for the Singular Learning Theory day. Thanks to Iliad and my coauthors @FurmanZach and Kai Ogden for making this intensive happen.
May 12
We just released the full course materials of the Iliad Intensive — a month-long, full-time AI alignment course for mathematicians, physicists, and theoretical computer scientists.
~20 contributors, 19 modules, at a depth that doesn't exist elsewhere for most of these topics. 🧵
1
7
517
Have you ever tried to look inside the run folders that W&B makes for every deep learning experiment?
Here's a deep dive about how I spent a few weeks freeing 118 GB of experimental archives from undocumented and corrupted binary .wandb files:
far.in.net/free-wandb
2
61
6 Oct 2025
I'm thrilled to be a part of delivering the first course on AI Safety and Alignment at the University of Oxford! Next week is going to be intense and I'm looking forward to it!
6 Oct 2025
🚨New AI Safety Course @aims_oxford!
I’m thrilled to launch a new called AI Safety & Alignment (AISAA) course on the foundations & frontier research of making advanced AI systems safe and aligned at @UniofOxford
what to expect 👇
robots.ox.ac.uk/~fazl/aisaa/
3
192
8 Jul 2025
At least for me, the big-picture motivation behind our RLC paper is a research vision for scalable AI alignment via minimax regret autocurricula.
Learn about the paper via co-author @Karim_abdelll: 🧵👉x.com/Karim_abdelll/status/1…
Learn about why I think this is important work 🧵👇
8 Jul 2025
*New AI Alignment Paper*
🚨 Goal misgeneralization occurs when AI agents learn the wrong reward function, instead of the human's intended goal.
😇 We show that training with a minimax regret objective provably mitigates it, promoting safer and better-aligned RL policies!
2
11
30
3,927
8 Jul 2025
For more complex environments, we still need better UED methods.
But UED is young!
There are plenty of plausible directions for improving over the methods that have been proposed so far.
The question is, is there enough room for improvement for this to help when it counts?
1
7
161
8 Jul 2025
Goal misgeneralisation remains an important risk model for future advanced AI systems.
We should continue to research how neural networks choose between different solutions and leverage that understanding into methods of avoiding unintended and dangerous solutions in the future.
8
137
8 Jul 2025
Our paper, "Mitigating goal misgeneralization via minimax regret," will appear at RLC 2025!
Congratulations to my co-authors @Karim_abdelll , @usmananwar391, @hannaherlebach, @casdewitt, @DavidSKrueger, and @MichaelD1729 🎉
Preprint out now arxiv.org/abs/2507.03068
Thread soon!
6
189
5 Jul 2025
There are many important social and ethical issues raised by today’s AI technologies. It's also true that as we project developments in AI technology into the future, we can foresee new and different ethical issues that might arise.
1
1
108
5 Jul 2025
Accordingly, last year, I was invited to give a guest lecture on ethical questions raised by potential future advancements in AI for the final week of @UniMelb's COMP90087 The Ethics of Artificial Intelligence.
youtu.be/-DvCQAiX2QA
1
141