more bangers from the greatest company to ever come out of YC (sorry stripe)
We formally verified 123 open-source projects in a partnership with Anthropic. Formal verification at scale is here!
Now we’re launching OSS Verify to scale it to the software we all depend on. We prove it’s crash-free or send you the patches it needs. Free for open-source. Let’s bootstrap the verified software ecosystem: theorem.dev/oss-verify
Dyusha Gritsevskiy retweeted
GLM-5.3 reasons that a misaligned action taken during training could be reinforced and make similar actions more likely later. It also considers what kind of agent it wants to be in the future, and factors this into how it should act. We call this "update-aware reasoning".
at this point the only conference I'll agree to review for is one where you have to swear an oath in front of a remote online notary, under penalty of a class 5 virginia felony with up to 10 years in prison, that you understand the details of your own submission...
total @DimitrisPapail victory once again
Fun fact: you can skiplag on the Northeast Regional. Boston to DC is $82; Boston to NYC on the same train is $116!
@grok does this have any sort of "contract of carriage violation" downside or can I just use this without worrying about it
Dyusha Gritsevskiy retweeted
METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
Dyusha Gritsevskiy retweeted
An update on Lean (auto)-formalization.
Speaking about my own research workflow, in 2026, we have gone from:
March: Lean formalization is not possible (for my papers).
May: Lean formalization is possible... but way too costly in time and tokens to be practical most of the time.
July: Lean formalization is now practical. I can probably formalize most of my papers now before they hit arxiv.
August: Lean formalization is now essential-- it increases efficiency of my workflow dramatically.
That is, the papers are getting written *informally* and finished much faster because of the Lean formalization.
























