Computational semantics and pragmatics, interpretability and occasionally some psycholinguistics. he/him. 🦝 https://sebschu.comhttps://bsky.app/profile/sebschu.bsky.socialhttps://bsky.app/profile/sebschu.bsky.social/post/3lsykdc24uc2tCan coding agents autonomously implement AI research extensions? We introduce RExBench, a benchmark that tests if a coding agent can implement a novel experiment based on existing research and code. Finding: Most agents we tested had a low success rate, but there is promise!02 Jul 2025 15:39 +0000at://did:plc:6p3rlfxd737o7ovnoe54hr3m/app.bsky.feed.post/3lsykdc24uc2t