

✓Member of the load-bearing staff


What do the recent agentic verification results mean for formal methods research? Read my thoughts on the PL Perspectives blog. P.S. I'm recruiting PhD students! blog.sigplan.org/2026/11/17/…

Today on PL Perspectives, Noam Zilberstein asks "What's going with program verification?" blog.sigplan.org/2026/11/17/…

Thanks for having me! Was a great discussion on what the current state is and what the future holds!

Emergent Behaviors with Gabe Orlanski, creator of SlopCodeBench: 🦄 AI That Works #81 x.com/i/broadcasts/2WXPoPRqB…

i’m increasingly of the opinion that almost everyone agrees with this, but a big fraction of people aren’t comfortable saying it in public, because of what it implies for the bean counting mechanism the whole machine is built on (for awards/promo/hiring/etc).

I am increasingly of the opinion that the academic paper is no longer a good medium for disseminating CS research. I think we should move to (1) blog posts and (2) books.

Any neurosymbolic tool developed today will be replaced with a better fully neural approach next year. Discuss

I’ve had an arxiv submission “on hold” for two months now. Second time this happens. @arxiv

insane alpha dump from @GOrlanski - slop code bench updates based on the Super fun working with the SCB team to run some of these benchmarks to support this research!

More concerningly, we see agentic slop moving higher up the stack. ESPECIALLY around library usage, where some agents choose to reimplement entire libraries, even when they can install them.

A few weeks ago, @dexhorthy released a great blog on how frontier agents performed on SlopCodeBench. Now, slop is moving up the stack and destroying your codebase with duplicate code.

The recent wave of formal verification results are analogous to the wave from 15 -20yrs ago with SAT/SMT: encode your verification problem in logic and call this magical solver. Now the magical solver is much much more powerful.


Announcing a major milestone achieved by my team @GoogleDeepMind: we have proven key security properties of the machine code underlying the Signal messaging protocol. This is the first time the actual production code of a widely deployed protocol has been formally verified – by any method, with or without AI – and at this depth. More than a research breakthrough, it’s a prime example of how frontier AI can be a force multiplier to counter the speed and scale of modern cyber threats. Formal verification offers a higher standard of security; however, it’s extremely complex and time consuming, which is why in many cases it’s considered to be impractical. Similar efforts could take teams decades of combined effort. We did it in a month’s time. Using AlphaProof Code, Google DeepMind's new agentic framework for formal verification that runs on LLMs including Gemini Carbon, we verified the Signal protocol down to the actual code running on devices. This milestone lays the groundwork for a future in which vital systems, from medical device firmware to power grid software, ship with mathematical proof that their protections work. Reaching that future will take continued research from our community. In that spirit, we're open-sourcing our formal specifications and verification artifacts so others can build on this work. On a personal note, this moment is of deep significance to me. I started my own research journey more than two decades ago as an intern working on checking the consistency of complex software systems. Seeing this grand challenge made practical with modern AI is extraordinary. I'm extremely proud of my team members: Swarat Chaudhuri, Andrew Ferraiuolo, Anton Kovsharov, Tej Chajed, Sam Schlesinger, Karn Seth, Jonathan Katz, and Charles Sutton for taking on this grand challenge and delivering, and grateful to the Signal team for their partnership. deepmind.google/blog/formal-…

my faculty applications research statement from over a decade ago…the formal verification dream is coming true