Found something good?

Save it before you doomscroll past it.

Can coding agents stay coherent over a 1 billion token budget?

Can they build Slack from scratch?
Rewrite a JAX codebase in PyTorch?
Build a C compiler in Rust?

Enter SWE-Marathon: a benchmark for autonomous long-horizon software work.

Tweet media
4659579517.2K
Keep it forever

Create a free account to save everything you preview — private to you.

Preview another link

Works with X, Instagram, TikTok & YouTube.

One place for everything
Tweets, TikToks, Reels, Shorts & articles in one searchable home.
Media at your fingertips
Full-screen viewer for photos and video — save any post to your collection.
Actually find it later
Full-text search across everything you save.
@rishi_desai2: "Can coding agents stay coherent over a 1 billion…" | ADHX