Large Language Models -- A Physicist's Perspective
A seminar by Tobias Osborne on orchestrating a swarm of coding agents to work on physics problems
In December I started experimenting with using Claude Code for physics calculations, and was playing with different methods for verifying their output. The buzz around Claude Code was huge, but I didn’t see many physicists using it, until I stumbled upon Tobias Osborne’s GitHub. I immediately contacted him, and have learned a lot from our discussions these past months. He recently visited us at UCL and gave a talk to the Physics department. We also held a few skill-sharing sessions. His talk is available on our YouTube channel, which we plan to relaunch in September (along with a new initiative at the interface of quantum information theory and gravity).
We’re in a funny time, where AI evangelists seem to think models are far better at physics and maths than they actually are. At the same time, many researchers completely underrate the power of frontier models — they tried ChatGPT once, found it unreliable and over-confident and haven’t engaged with more recent coding agents.
The truth lies in between. These models are neither geniuses nor useless, and you need to know the physics well to understand where they fail. I completely agree with Tobias when he describes coding agents as hyperactive Masters students. They’re fast and relentless, but very unreliable. So finding ways to verify their output is important. But with a bit of scaffolding around these models and domain expertise, you can make them more reliable. I highly recommend Tobias’s talk, especially if you’re new to using coding agents for tasks outside of software engineering.
You can find the slides of Tobias’s talk on his GitHub. During the talk he mentions a story about me getting Claude to reveal its system prompt (the hidden instructions that tell the model how to behave, before you even type anything). That was a wild conversation, so I’ve posted it here. The demo he gives during his talk can be found on his GitHub too. We’ve confirmed with some experts that Claude Code did make a reasonable start on a very hard problem.
As always, we are entering both an exciting and terrifying period. If you want to see what some of the fuss is about, watch Tobias’s talk, and find details of Tobias’s and other upcoming seminars on our seminar page.
there is a typo in the hyperlink for the pdf file, with a ")" at the end, which breaks the link
We are currently working on a hypothesis, we are not looking for a creator only the fingerprints left behind. (Osim forensic cosmology v2.2). It seems to be a biological loop not a silicon simulation and since the University of British Columbia has found that the Non-Algorithmic Wall says reality can't be digital our independent research group from Oklahoma has been looking into biological systems being the most efficient material in existence. Biology is millions of times more efficient than any computer chip which could suggest it's a biological loop (Life-Raft) not a digital matrix. The Big Bounce which some new researchers this week in April 2026 are suggesting wasn't just a big bang one time but an infinite bounce. (Cyclical). if that is proven it turns our hypothesis into reality because if you have an infinite bounce and we are here now talking about this then 1 x infinite = infinite so this will happen infinitely. If it is a big numbers game it is not just likely it is mathematically guaranteed. This would also show that it is not a multi-universe( mutiverse )because since it is biological it wouldn't be recreated in itself but instead resetting the same physical system over and over , Our team is just documenting the Sovereign Blueprint of how this works and we think seeing the universe as a highly efficient biological Life-Raft where humanity seems to be the prime reason for the system changes the whole conversation because the data is showing that we are the hardware not the software. It is falsifiable , if the universe is proven to keep expanding then the big freeze wins and osim is proven wrong, or if silicon or another material can mimic life and be more efficient than biological systems then osim is proven wrong. We are officially moving away from the "creator" or " programmer " and focusing on the forensic cosmology blueprint.....(Oklahoma sim theory osim Sovereign Inception Model) forensic cosmology. We are currently watching the research from Simon's observatory to see if they find evidence of the big bounce (cunch).also looking at dark matter to see if it acts as scaffolding (roadmap) for universe after each bounce. We would appreciate any feedback. Thank you.