Charles Sutton

Research scientist @GoogleAI / Previously academic @InfAtEd / Deep learning to help people write code. / @[email protected] / ❤️s:🐱🐶☕️🍕

[Charles Sutton @RandomlyWalking]

New blog on how to manage stress as a researcher: If you really are an impostor, it's not a syndrome. https://t.co/FuNjfN9Fvn

[Charles Sutton @RandomlyWalking]

More context on the story behind the work and the theam. It has been such a wonderful experience working with this team --- great researchers and great humans, all!
https://t.co/EmQrgbySs7

[Swarat Chaudhuri @swarat]

Thrilled to announce that our @GoogleDeepMind team has cracked a major challenge in software engineering and cybersecurity: formally verifying a real-world implementation of the #Signal cryptographic protocol at the machine-code level. This proof was done using AlphaProof Code, our new AI framework for formal specification and verification.

* Paper: https://t.co/mq5WyFl4jb
* Lean code: https://t.co/u4UIl154AY
* DeepMind blog post: https://t.co/eBxLMPlIDJ

A huge shoutout to my amazing teammates: @tchajed,
@FerrousAndrew, Jonathan Katz, @pushmeet, @antonkovsharov, Karn Seth, Sam Schlesinger, @RandomlyWalking.

I started working on formal software verification 20+ years ago as a grad student. I was persuaded by Dijkstra and other computer science pioneers’ vision of programming backed up by mathematical theorems. At that time, we had to choose between automated code analysis algorithms that scaled but could only prove shallow properties, and deep manual verification that took decades of expert human work.

Thanks to progress in AI for mathematical reasoning, we don’t have to make that choice any more. Over four weeks in October 2026, AlphaProof Code agents generated more than 6 million lines of machine-checked Lean proof. We proved deep computational and symbolic security properties of the entire protocol core of Signal, all the way down to the ARM machine-code level.

This is just the first step, of course, because our goal is nothing short of verifying the world’s software infrastructure. Most cyberattacks, including the AI-powered ones recently in the news, happen because of preventable code bugs. I expect that agents for formal code analysis will eliminate these bugs one category at a time.

As our paper explains in more detail, this doesn’t at all mean humans are out of the picture! Proofs are now largely automated, but human experts will need to decide what is proved with AI assistance. AlphaProof Code offers an early glimpse of what such human-AI collaboration could look like, but many other proposals of this nature will emerge.

We have released all our Lean specs and proofs and plan to work with the open-source community on improving them. If you are building critical software and would like to apply these ideas, come talk to us!

[Charles Sutton @RandomlyWalking]

Delighted to share the the work of my team at
@GoogleDeepMind: formally verifying a real-world implementation of the #Signal cryptographic protocol at the machine-code level. The proof was done using AlphaProof Code, our new AI framework for formal specification and verification.

[Sundar Pichai @sundarpichai]

Our teams put Gemini 4 Carbon to work on a major security challenge: mathematically proving the code underlying the Signal protocol.

Using AlphaProof Code, @GoogleDeepMind researchers guided agents to verify the protocol down to compiled device code, closing the gap where real bugs hide. The result:

- Gemini 4 Carbon generated over 6M lines of machine-checked Lean proofs
- years of expert manual verification compressed to just weeks
~1% of the codebase required human review (Lean automatically checked the rest)

This is helping unlock scalable formal verification for building secure software, laying the groundwork to fundamentally shift the advantage to defenders. We’re open sourcing the results for the security community.

[Charles Sutton @RandomlyWalking]

@TaliaRinger @swarat @GoogleDeepMind Indeed!

[Charles Sutton @RandomlyWalking]

@liyuajia All the best, we will miss you! Enjoy your time in the garden, can't wait to see what you do after that!

[Charles Sutton @RandomlyWalking]

@Pinboard @kaepora It's the only way to be sure

[Varun Mohan @_mohansolo]

Excited to launch Google Antigravity, our next generation agentic IDE, now powered by Gemini 3!

[Quoc Le @quocleix]

Gemini 3 is finally out. 🚀

The numbers on the hardest benchmarks are wild. Seeing MathArena Apex go from <2% to 23.4% and ARC-AGI-2 hit 31% feels like a real turning point for reasoning. We're starting to crack problems that used to look impossible.

Huge congrats to the team.

[Heather Adkins - Ꜻ - Spes consilium non est @argvee]

We’re excited to see the security and OSS communities engage on vulnerability disclosure in light of new AI technologies that we believe will enable both defenders and attackers alike. Existing and emerging norms around disclosure are important debates, and we’ve noted the feedback. Thanks! Also want to share some additional thoughts. 1/10

[Kevin Patrick Murphy @sirbayes]

I am pleased to announce our new paper, which provides an extremely sample-efficient way to create an agent that can perform well in multi-agent, partially-observed, symbolic environments.

The key idea is to use LLM-powered code synthesis to learn a code world model (in the form of Python code) from a small dataset of (observation, action) trajectories, plus some background information (in text form), and then to pass this induced WM, plus the observation history, to an existing solver, such as (information-set) MCTS, to choose the next action.

[Royal Hansen @royalhansen]

Initial results from a large scale run of @Google Big Sleep are here!Our AI agent found a series of vulnerabilities in widely used & reviewed software,demonstrating a new frontier in automated vulnerability discovery.Full details once the issues are fixed: https://t.co/9OIAffoatb

[Heather Adkins - Ꜻ - Spes consilium non est @argvee]

Today as part of our commitment to transparency in this space, we are proud to announce that we have reported the first 20 vulnerabilities discovered using our AI-based "Big Sleep" system powered by Gemini — https://t.co/0sgPlazqaq

[Charles Sutton @RandomlyWalking]

@scuzzlebot @YiyuanLi1 In my experience, actual gardening requires a combination of extensive knowledge (sounds interesting) and hard manual labor (not a fan). Metaphorical gardening is much less taxing.

[Charles Sutton @RandomlyWalking]

New blog! Advice about career and creativity for researchers and engineers. This time: What my PhD in computer science taught me about gardening. https://t.co/V914t8DMdc

[Arvind Narayanan @random_walker]

Back in grad school, when I realized how the “marketplace of ideas” actually works, it felt like I’d found the cheat codes to a research career. Today, this is the most important stuff I teach students, more than anything related to the substance of our research.

A quick preface: when I talk about research success I don’t mean publishing lots of papers. Most published papers gather dust because there is too much research in any field for people to pay attention to. And especially given the ease of putting out pre-prints, research doesn’t need to be officially published in order to be successful. So while publications may be a prerequisite for career advancement, they shouldn’t be the goal. To me, research success is authorship of ideas that influence your peers and make the world a better place.

So the basic insight is that there are too many ideas entering the marketplace of ideas, and we need to understand which ones end up being influential. The good news is that quality matters — other things being equal, better research will be more successful. The bad news is that quality is only weakly correlated with success, and there are many other factors that matter.

First, give yourself multiple shots on goal. The role of luck is a regular theme of my career advice. It’s true that luck matters a lot in determining which papers are successful, but that doesn’t mean resigning yourself to it. You can increase your “luck surface area”.

For example, if you always put out preprints, you get multiple chances for your work to be noticed: once with the preprint and once with the publication (plus if you’re in a field with big publication lags, you can make sure the research isn’t scooped or irrelevant by the time it comes out).

More generally, treat research projects like startups — accept that there is a very high variance in outcomes, with some projects being 10x or 100x more successful than others. This means trying lots of different things, taking big swings, being willing to pursue what your peers consider to be bad ideas, but with some idea of why you might potentially succeed where others before you failed. Do you know something that others don’t, or do they know something that you don’t? And if you find out it’s the latter, you need to be willing to quit the project quickly, without falling prey to the sunk cost fallacy.

To be clear, success is not all down to luck — quality and depth matter a lot. And it takes a few years of research to go deep into a topic. But spending a few years researching a topic before you publish anything is extremely risky, especially early in your career. The solution is simple: pursue projects, not problems.

Projects are long-term research agendas that last 3-5 years or more. A productive project could easily produce a dozen or more papers (depending on the field). Why pick projects instead of problems? If your method is to jump from problem to problem, the resulting papers are likely to be somewhat superficial and may not have much impact. And secondly, if you’re already known for papers on a particular topic, people are more likely to pay attention to your future papers on that topic. (Yes, author reputation matters a lot. Any egalitarian notion of how people pick what to read is a myth.)

To recap, I usually work on 2-3 long-term projects at a time, and within each project there are many problems being investigated and many papers being produced at various stages of the pipeline.

The hardest part is knowing when to end a project. At the moment you’re considering a new project, you’re comparing something that will take a few years to really come to fruition with a topic where you’re already highly productive. But you have to end something to make room for something new. Quitting at the right time always feels like quitting too early. If you go with your gut, you will stay in the same research area for far too long.

Finally, build your own distribution. In the past, the official publication of a paper served two purposes: to give it the credibility that comes from peer review, and to distribute the paper to your peers. Now those two functions have gotten completely severed. Publication still brings credibility, but distribution is almost entirely up to you!

This is why social media matters so much. Unfortunately social media introduces unhealthy incentives to exaggerate your findings, so I find blogs/newsletters and long-form videos to be much better channels. We are in a second golden age of blogging and there is an extreme dearth of people who can explain cutting-edge research from their disciplines in an accessible way but without dumbing it down like in press releases or news articles. It’s never too early — I started a blog during my PhD and it played a big role in spreading my doctoral research, both within my research community and outside it.

Summary
* Research success doesn’t just mean publication
* The marketplace of ideas is saturated
* Give yourself multiple shots on goal
* Pick projects, not problems
* Treat projects like startups
* Build your own distribution

[Charles Sutton @RandomlyWalking]

@YiyuanLi1 Thanks for catching the typo!

My take: Weeds are plants that are unwanted. If you like them, they are no longer weeds!

[Charles Sutton @RandomlyWalking]

@Stefania_druga I haven’t! Thanks for the recommendation!

[Jonathan Lee @jon_lee0]

I’m excited to share the news of Gemini Deep Think’s gold-medal level performance 🥇 at the International Math Olympiad! It has been an absolute blast building Deep Think this year and then scaling it to the IMO.

[Charles Sutton @RandomlyWalking]

@y0b1byte Haha, you found that fast! Thanks for the kind words!

[yobibyte @y0b1byte]

Great post by @RandomlyWalking

[Charles Sutton @RandomlyWalking]

@YiMaTweets And what was your answer?