As part of SIGPLAN blog, Adrian Sampson and I started an interview series where we talk to PL luminaries. Our first one is a super fun conversation with Ranjit Jhala (Ranjit Jhala). 1h26m of goodness. youtube.com/watch?v=goUZcz…

Excellent analysis by Soham Sankaran! Lays down the urgent problems, and the ambitious path India should take

Look ma, my LLM will reach AGI in 6 months

Compilers textbooks tend to present the various context-free parsing algorithms completely separately and it's hard to see where they come from. Why does shift-reduce parsing look so different from recursive-descent? You can understand all of them as simply refinements of...

Who would have known

Something's cooking 🧑‍🍳

Visiting BLR next week. Let me know if you are around and want to meet

We’re not poor. We’re scared. Soham Sankaran's piece was a gut punch and a provocation. I wrote this response from the POV of an Indian early-stage VC. Why the system breaks, where founders keep going anyway, and how we can fix it. Thank you Soham Sankaran. This is for the

Here's a paper describing quantum computing using standard programming constructs, w/o linear algebra! Goal: demystify quantum computing + serve as a formal foundation for reasoning about quantum programs. paper paper eprint.iacr.org/2025/1091.pdf code github.com/qqq-wisc/qwla

New paper: World models + Program synthesis by Wasu Top Piriyakulkij 1. World modeling on-the-fly by synthesizing programs w/ 4000+ lines of code 2. Learns new environments from minutes of experience 3. Positive score on Montezuma's Revenge 4. Compositional generalization to new environments

I have been coming around to this. Program synthesis for software is equivalent to a higher-level language compiler for programmers. The real unlock enables domain experts (like scientists) to use computation to model phenomena, speed up analysis, interoperability

Don’t talk R&D, please, we are Indian industry.

AI first languages will get more value by making testing a first class citizen not formal verification

Are code agents good at software design, ie building general and reusable code? We present Librarian, a new refactoring method, and MiniCode, a verifiable refactoring benchmark that requires agents to design libraries that jointly minimizes code from multiple repos 🧵

Me, when some joker says AI is a waste of time because we have traditional static analysis.

Can transformers analyze code efficiently? ✅ Yes. We prove transformers efficiently handle real compiler tasks (AST construction, symbol resolution, type infer) using only log size—while RNNs require linear size (in input length). Paper: arxiv.org/abs/2410.14706 #COLM2025

New Galois blog: “Specifications Don’t Exist”. If we want to formally verify more systems, we need formal specifications, but most real systems are hard to specify for very deep reasons

AI will kill software engineering jobs Meanwhile software at the AI company:

AOL says it will discontinue dial-up internet on September 30 May this sound echo in eternity:

monads are only free if your time is worthless