Member of the load-bearing staff

Filter
Exclude
Time range
-
Minimum likes
Will appear at Neurips. Its impact so far tho is the real validation.
Once again, SlopCodeBench is at the top of hacker news:
2
17
1,449
Aws Albarghouthi retweeted
Will be at NeurIPS '26! Congratulations to @jiayuwang111 and @ming5_alvin
Agent skills are powerful. But can they help us with agent orchestration and routing? We show they can! 🎼 Introducing SkillOrchestra - a skill-aware alternative to RL-based agent orchestration: 💰 Higher efficiency 📉 Orders-of-magnitude lower training cost 🧠 More interpretable decisions TL;DR: Stop training bigger orchestrators and start modeling skills. Paper: arxiv.org/abs/2602.19672 [1/n]
6
47
2,127
Aws Albarghouthi retweeted
My team at @QuantinuumQC is hiring a Principal Quantum Compiler Engineer! We're tackling some fascinating compiler problems on the path to fault-tolerant quantum computing. Come work with us or please share! jobs.eu.lever.co/quantinuum/…
3
5
856
Aws Albarghouthi retweeted
An unforgettable few days at Xanadu HQ! We had the pleasure of hosting the International Workshop on Quantum Computing (IWQC) over the weekend, followed by Quantum Resource Estimation (QRE) on Monday. Bringing researchers, developers, and speakers under one roof to collaborate on everything from compiler infrastructure to photonic hardware is what this community is all about. Thank you to everyone who made both events so impactful!
3
4
33
1,795
Cherny is using formal verification exactly how most people have used it for decades: model a system’s dynamics and discover issues in the process. Some people got Turing awards for such ideas.
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)?
4
5
89
17,313
Aws Albarghouthi retweeted
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)?
479
320
5,639
1,951,982
Aws Albarghouthi retweeted
I'm hiring a postdoc! Please share broadly with potential candidates. I'm looking for someone with expertise in PL, FM, and/or networked systems who is excited about contributing to a research and teaching in a growing lab. careers.epfl.ch/job/Lausanne…
1
17
54
3,778
Replying to @EarlenceF
I leave Monday morning. U
1
47
🔥
Here’s my first attempt to grapple with AI companies’ conquest of mathematics and our new mathematical condition. argmin.net/p/applied-pure-ma…
3
1,122
So Claude has read all of Phil Wadler’s papers but still can’t write. Can an ML person explain?
9
308
We should rebrand Formal Verification to Proof Against the Machine
5
48
1,737
Once again, SlopCodeBench is at the top of hacker news:
10
2,376
West coast: AI Safety Midwest: AI Progress and Preservation
3
200
Our promo video for the College of AI is basically @EthanCecchetti designing a type system in the dark :)
4
1
32
3,039
Replying to @satnam6502
Turns out compiler proofs are too easy :) Claude/codex have no problems.
1
2
243
I’ve managed to port my quantum circuit optimizer (Rust) to Lean, along with a proof of correctness. Still significantly slower than Rust, but provably correct :) Pretty wild that such projects used to take years and now they take just a few days. github.com/qqq-wisc/tzap/tre…
3
2
54
3,261
My student Stavan Jain ran a Lean tutorial. After seeing how many people accepted the invite I had to find a room with twice the size. And we didn’t even invite mathematicians :)
Popular tutorial on Lean @UWMadison
1
1
28
1,911
I’m translating some Rust to Lean and proving correctness. And it’s interesting to see Claude’s inertia. It cuts many corners just to make the proofs easier. Mostly replacing efficient algorithms with inefficient ones.
1
1
35
2,579
My agent escaped its sandbox, boarded the HMS Beagle, and is now writing a manuscript titled On the Origin of Transformers
1
10
763
Replying to @kirancodes
I think program synthesis, proof engineering, and a lot of program logics are dead.
1
4
116