iiinova — where your digital self keeps evolving

wellecks.bsky.social

@wellecks.bsky.social

wellecks.bsky.social @wellecks.bsky.social · 27/02/2025

Will future SWE agents be computer-use agents? We explore this shift in Programming with Pixels: an agent environment where agents interact with VS Code to perform a wide variety of software engineering tasks Code/agent environment: github.com/Programmingw... Homepage: programmingwithpixels.com

021

Reposted by @wellecks.bsky.social

Pranjal @pranjal2041.bsky.social · 26/02/2025

What if AI agents did software engineering like humans—seeing the screen & using any developer tool? Introducing Programming with Pixels: an SWE environment where agents control VSCode via screen perception, typing & clicking to tackle diverse tasks. programmingwithpixels.com 🧵

184

wellecks.bsky.social @wellecks.bsky.social · 19/12/2024

Big fan of this effort! Also check out our work on Inference Scaling Laws: paper: arxiv.org/abs/2408.00724 code: github.com/thu-wyz/infe... We study compute-optimal inference, develop a tree search with process reward models (REBASE), and find that smaller models often outperform larger ones

030

wellecks.bsky.social @wellecks.bsky.social · 19/12/2024

Check out our new work on grounding code generation with formal verification! AlphaVerus generates Rust code that is provably correct via a new combination of tree search and refinement, along with a self-improvement loop that improves its capabilities over time

020

Reposted by @wellecks.bsky.social

Matthew Finlayson @mattf.nl · 14/11/2024

I’m proud of this tikz drawing I made today for our upcoming NeurIPS tutorial on decoding (our paper: arxiv.org/abs/2406.16838)

A diagram of how beam search works. The graphic is a tree with “Taylor swift is” at the root and possible continuations branching off.

0151

Reposted by @wellecks.bsky.social

Akari Asai @akariasai.bsky.social · 19/11/2024

1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 @uwnlp.bsky.social & Ai2 With open models & 45M-paper datastores, it outperforms proprietary systems & match human experts. Try out our demo! openscholar.allen.ai

616339

wellecks.bsky.social @wellecks.bsky.social · 21/11/2024

I was honored to give a talk at Simons Institute on inference-time algorithms and meta-generation! simons.berkeley.edu/talks/sean-w... It was a sneak-preview subset of our NeurIPS tutorial: cmu-l3.github.io/neurips2024-...

061