Member of the load-bearing staff
Joined October 2009
- Tweets2.2K
- Following898
- Followers2.5K
- Likes11.1K
Aws Albarghouthi retweeted
I've discovered that all popular quantum computing SDKs / compilers have serious bugs when it comes to handling angles -- floating point strikes again!
IBM's Qiskit, Google's Cirq, Rigetti's quilc, IQM's Qrisp, NVIDIA's CUDA-Q, Xanadu's PennyLane, qBraid's SDK, ...
🧵1/n
Aws Albarghouthi retweeted
Models are sycophantic, and when they do challenge faulty or incorrect inputs, they're ambiguous and ineffective.
In a new paper w/ multilingual co-authors, we find that people may view LM responses that push back, yet still end up believing false content is true.
ALT A screenshot of the top half of the first page of a paper titled "Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively" with authors Li Lucy, Myra Cheng, Svenja Guhr, Kabir Ahuja, Orevaoghene Ahia, Sameep Chattopadhyay, Yike Wang, Valentin Hofmann, Noah A. Smith, Yulia Tsvetkov
Aws Albarghouthi retweeted
More cake to celebrate Francis Halzen’s well-deserved Nobel Prize @NobelPrize ! 🎂 Proud to be part of UW–Madison Physics @UWMadPhysics, where extraordinary science continues to happen. Here’s to more discoveries—and more milestones worth celebrating—in the years ahead!
Aws Albarghouthi retweeted
New blog post on PL perspectives by Max Willsey:
Equality Saturation: An “incomplete” project
blog.sigplan.org/2026/10/01/…
Aws Albarghouthi retweeted
From the (excellent) WSJ obit of Margaret Hamilton: she left behind 2^0 daughters, 2^1 grandsons, and 2^2 great-grandchildren. Total boss behavior.
ALT https://www.wsj.com/science/space-astronomy/margaret-hamilton-who-developed-software-for-first-moon-landing-dies-at-90-07b982a1
Aws Albarghouthi retweeted
I’m at #COLM2026! If you’re excited about the science of LLMs or scaling laws, feel free to reach out for a time to chat!
Tomorrow at 4:30 PM, I’ll be presenting our work showing that joint pretraining and test-time scaling makes overtraining compute optimal. @COLM_conf 🦙
Aws Albarghouthi retweeted
I will be in SF for #COLM2026 on Tue & Wed. Then, on Thursday, I'll present SlopCodeBench at @SnorkelAI's Frontier Data Summit.
Always happy to chat about evaluations, agents for code, or just general long-horizon agentic tasks! (Also: on the job market this spring!)
Aws Albarghouthi retweeted
We are hiring a Quantum Scientist - Compilation to join Xanadu’s software and algorithms group and work with our team of scientists and developers to design cutting-edge quantum algorithms.
In this role, you will help build one of the world’s most advanced software platforms for quantum computing by designing compilation architectures, optimizing compilation passes, inventing key IP, and publishing scientific papers.
Sound like your next role? Learn more and apply today: xanadu.careers.hibob.com/job…
Aws Albarghouthi retweeted
Many libraries nowadays are agent-written, so a natural question is whether they can design & use these libraries effectively. It’s important to track this behavior, especially as agents continue to be used for coding.
Awesome work by @GOrlanski that I got to play a role in!
Aws Albarghouthi retweeted
Check out the leaderboard at ldbench.com!
Paper: arxiv.org/abs/2609.36730
Repo: github.com/SprocketLab/libra…
HF Papers: huggingface.co/papers/2609.3…
Blog: gabeorlanski.github.io/posts…
Aws Albarghouthi retweeted
Agents will soon replace humans as the main users and designers of libraries.
A good library will let future agents write correct programs with less code.
Introducing LibraryDesignBench: one agent designs a library, and other agents write programs with it.
Aws Albarghouthi retweeted
(1/2) Possibly contrary take: we need academic-style research more than ever going forward. The recent AI cyber-insecurity incidents illustrate that we have created agents that do unexpected things in unexpected ways (e.g., messageboards); we do not understand or control.
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]
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/…
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!
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)?
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…
