Joe retweeted
After 5 months, 385 citations, and 50 pages I’m excited to finally share the preprint of the survey paper my collaborators and I have been working on:
sainati.pl/gpu-survey-prepri…
We wanted to put it on arXiv but tragically they don't take survey papers anymore.
Just landed at SFO. Will be at SPLASH this week! I’m here in my dual capacities as (a) co-author of “Fail Faster: Staging and Fast Randomness for High Performance PBT”, and (b) employee of the tee shirt company!
Home from SPLASH. Sorry for all the folks I wanted to catch up with but didn’t! It was a 3 day trip and I was sort of sick for the first 1.5 days :(
But saw a lot of fun stuff in the final 1.5 days.
> i ask Claude if the program is verified
> he says yes
> i ask if he verified the program or a smaller, better-behaved program he imagined
> he laughs and says “it’s verified sir”
> i use the program
> it has a bug
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached.
TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt.
I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted.
Is formal verification the future of coding (or at least, bug finding)?
Joe retweeted
100 problems is nothing, in programming languages we routinely solve exactly the next 700 problems
Unbelievably cool job
We're hiring developers to work on Hegel (property-based testing for ~every language) in London with me, and are struggling a bit to source candidates, so I wrote a less professional post about why this is the coolest job ever and you should apply.
drmaciver.com/2026/09/come-w…
In 2022 I watched Tiafoe lose a brutal match to Kyrgios in front of a hometown crowd at the DC open. Been a big fan of his ever since. Hard to watch him lose again last night :(
Look forward to the day he makes a major final.
So the “10% it kills everyone” people. What do they think P(it kills 5% of people in a year) is?
Surely they can’t believe “either nobody or everybody dies w.p. 0.1”
Ok. I’m locked in. I’m Monitoring The Situation. One of my monitors is the Situation Monitoring monitor














