←
Freddie Bickford Smith220 posts
Freddie Bickford Smith avatar

Freddie Bickford Smith

@fbickfordsmith

ML postdoc at Oxford with @tom_rainforth

◷ Joined June 2011▧ 8 Photos and videos
Andreas Kirsch 🇺🇦 avatar
⟳ Freddie Bickford Smith retweeted
Andreas Kirsch 🇺🇦@BlackHC·Oct 21

The non-disparagement clauses in Google's UK employment contracts are indeed incredibly broad. This is from the Confidentiality and Proprietary Information Agreement I signed in 2024 before I started. It forbids any criticism forever (regardless if it's true or not)

Post attachment
Branton DeMoss avatar
⟳ Freddie Bickford Smith retweeted
Branton DeMoss@BrantonDeMoss·Aug 19

Nice thread on entropy and uncertainty, but see @fbickfordsmith's excellent paper Rethinking Aleatoric and Epistemic Uncertainty for the decision-theoretic take, where uncertainty is defined as the expected loss under the Bayes-optimal policy! arxiv.org/abs/2412.20892

For many of us, the first time we see Shannon’s entropy H(X) = −Σᵢ pᵢ log pᵢ feels magical. Sure, it has many beautiful properties, but why should this particular formula measure “uncertainty”? Can we define uncertainty first and derive the formula afterward?

Jon Barron avatar
⟳ Freddie Bickford Smith retweeted
Jon Barron@jon_barron·Jan 28

This idea that intelligence is solely a function of what you've observed since birth and not also a function of the 500 million years of evolution that preceded your birth is surprisingly sticky despite being demonstrably untrue.

The proof that this is possible is all around us: whereas current systems are trained on essentially all of accessible history, humans exceed AI capabilities despite seeing at most a few billion text tokens by adulthood.

Jannik Kossen avatar
⟳ Freddie Bickford Smith retweeted
Jannik Kossen@janundnik·1 Dec 2025

Come and check out our work on how to evaluate LLMs with less compute and fewer labels! Find first author Gabrielle at EurIPS or Freddie and I at poster 110 at the 11 AM session on Friday.

Active testing enables label-efficient model evals but can be computationally expensive. We show how to reduce costs and scale up to LLMs. arxiv.org/abs/2508.09093 Work led by Gabrielle Berrada. Find her at EurIPS, or @janundnik and me at NeurIPS in San Diego.

Post attachment
Timothy Gowers @wtgowers avatar
⟳ Freddie Bickford Smith retweeted
Timothy Gowers @wtgowers@wtgowers·31 Oct 2025

I crossed an interesting threshold yesterday, which I think many other mathematicians have been crossing recently as well. In the middle of trying to prove a result, I identified a statement that looked true and that would, if true, be useful to me. 1/3

Toby Ord avatar
⟳ Freddie Bickford Smith retweeted
Toby Ord@tobyordoxford·20 Oct 2025

New post on RL scaling: Careful analysis of OpenAI’s public benchmarks reveals RL scales far worse than inference: to match each 10x scale-up of inference compute, you need 100x the RL-training compute. The only reason it has been cost-effective is starting from a tiny base. 🧵

Post attachment
Helen Toner avatar
⟳ Freddie Bickford Smith retweeted
Helen Toner@hlntnr·10 Oct 2025

Every so often, OpenAI employees ask me how I see the co now. It's always tough to give a simple answer. Some things they're doing, eg on CoT monitoring or building out system cards, are great. But the dishonesty & intimidation tactics in their policy work are really not. E.g:

One Tuesday night, as my wife and I sat down for dinner, a sheriff’s deputy knocked on the door to serve me a subpoena from OpenAI. I held back on talking about it because I didn't want to distract from SB 53, but Newsom just signed the bill so... here's what happened: 🧵

Post attachment
Oxford Statistics avatar
⟳ Freddie Bickford Smith retweeted
Oxford Statistics@OxfordStats·26 Aug 2025

With @JesusOxford we are looking for a Professor of Statistics. Become part of a historic institution and a community focused on academic excellence, innovative thinking, and significant practical application. About the role: tinyurl.com/b8uy6mr5 Deadline: 15 September

Post attachment
Cas (Stephen Casper) avatar
⟳ Freddie Bickford Smith retweeted
Cas (Stephen Casper)@StephenLCasper·24 Aug 2025

Research on AI "sandbagging" is getting more popular recently. In this 🧵, I'll give some reasons that I think it's not a useful research paradigm. TL;DR, I think it's a confusing reframing of fairly well studied and previously solved problems.

David Krueger 🦥 ⏸️ ⏹️ ⏪ avatar
⟳ Freddie Bickford Smith retweeted
David Krueger 🦥 ⏸️ ⏹️ ⏪@DavidSKrueger·9 Aug 2025

It's great the governments (and others) continue to demonstrate that the models companies release are incredibly insecure. It's terrible that governments aren't penalizing companies for releasing such insecure models, and instead just help them patch them.

We at @AISecurityInst worked with @OpenAI to test GPT-5's safeguards. We identified multiple jailbreaks, including a universal jailbreak that evades all layers of mitigations and is being patched. Excited to continue partnering with OpenAI to test & strengthen safeguards.

Post attachment
Lorenz Kuhn avatar
⟳ Freddie Bickford Smith retweeted
Lorenz Kuhn@_lorenzkuhn·11 Aug 2025

Just two years ago, our smartest models could barely solve the easiest competitive programming problems. Last week, our latest reasoning models achieved a gold medal score at the International Olympiads of Informatics. Competitive programming is one of the cleanest examples of scaling up RL training for LLMs. Soon, with experimental approaches like the one used for IMO, we might see similar scaling on real-world coding problems.

1/n I’m thrilled to share that our @OpenAI reasoning system scored high enough to achieve gold 🥇🥇 in one of the world’s top programming competitions - the 2025 International Olympiad in Informatics (IOI) - placing first among AI participants! 👨‍💻👨‍💻

Post attachment
William MacAskill avatar
⟳ Freddie Bickford Smith retweeted
William MacAskill@willmacaskill·4 Aug 2025

Today I’m releasing an essay series called Better Futures. It’s been something like eight years in the making, so I’m pretty happy it’s finally out! It asks: when looking to the future, should we focus on surviving, or on flourishing?

Post attachment