Sai (@cydatio) profile picture
sf
Joined May 2024
Photo by Sai (@cydatio)Photo by Sai (@cydatio)Photo by Sai (@cydatio)Photo by Sai (@cydatio)
Sai retweeted
Software Verification in Lean (SVIL) comes to Stanford University on Saturday, November 7. Co-organized by Beneficial AI Foundation and Lean FRO, it is a day of public lectures on advancing Lean’s software verification ecosystem toward production use, with a focus on end-to-end verification of security-critical systems. Talks will cover Rust verification with the Aeneas framework, low-level software verification, and formally verified OS kernels. Speakers include Max Tegmark, Shaowei Lin, Leonardo de Moura, Jonathan Protzenko, Andres Erbsen, and Mike Dodds. In-person space is limited. Non-local and waitlisted registrants will receive a livestream link, and recordings will be available afterward. Program and registration: beneficial-ai-foundation.git…
4
61
2
365
33,520
We’re organizing Vibecheck, a formal methods hackathon with some of the best folks in the space - @maxvonhippel, @qd_forall, @nolanlwin, @jessemhan, @emiyazono, and @workersio. You’ll get a weekend to build real production software, and formally verify it. We’ll have people who really know their stuff around to help, and you can come with a team, find one there, or just hack on something yourself. We are glad to have a phenomenal group of sponsors, including @harmonicmath, @mathematics_inc, @theoremlabs, @thegp, @omnicom, @primeintellect, @astriolabs, @buildwithparty, @wearerandomlabs, and @lanyon_ai, as well as some more we will announce in the coming days! If you’re a hacker, a formal methods person, or just someone who thinks “how do we know it works?” is an interesting question, we’d love to have you. Signup Now: fmxai.org/vibecheck/
21
41
21
207
78,191
Sai retweeted
Thank you to everyone who spent their Saturday with us at Ebolathon—and congratulations to the BuilderBlockers, Michael, @cydatio, and Rafal, who took an interesting synthon-aware Thompson Sampling approach to guide compound selection. All submissions have been sent to our co-host, @onepot_ai, for synthesis before moving into pseudovirus assay testing. All assay data will be made public. A special thank you to our judges—@andrei_tyrin, Andrii Kyrylchuk, Amy He, and Nina Jovic—for lending their time and expertise. And thank you to our sponsors—@RowanSci, @boltz_bio, @OpenRouter, @modal, and @anyscalecompute for giving participants access to the models and compute needed to explore the challenge, and to @posthog for hosting us in their wonderful space!
3
8
2
26
2,525
A little on the nose for the agent era (from The Art of Doing Science and Engineering):
2
174
“Data analysis is the gateway to scientific reasoning” generalizes to non-scientific domains as well imo
1
2
236
I swear every couple of months I come across a Borges reference lol. I’m gonna sit down and read a collection of his works someday. Also, good post
New blog post: "A sufficiently detailed spec is code" I wrote this because I was tired of people claiming that the future of agentic coding is thoughtful specification work. As I show in the post, the reality devolves into slop pseudocode haskellforall.com/2026/03/a-…
2
237
What was the pre-LLM version of “oh, it’s just ai slop”? “oh, it’s just propaganda”?
44
This is my main dilemma. How much time and effort should I spend expanding an approach that works/brings value now vs trying to get something that can potentially better leverage model capabilities now + in the future but will take longer/be harder to control?
2
83
I guess though this is just how SWE has always been. Just a new set of tradeoffs to consider. Though coding agents def help with the experimentation
30
And how can I make the transition more incremental so I can keep taking advantage of model capabilities?
31
Has anyone tried RLMs on data analysis tasks or on tabular data/manipulating data frames? Feels like I'm having to get pretty detailed in the system prompt (GPT 5.1) on analysis strategy/task decomposition/context to give to sub-LLMs @a1zhang @omouamoua
1
2
426