Coding Agents Are Making Hypothesis Testing Cool Again in NLP Papers, Reviewer Observes
deliprao · x · 2026-09-16
Delip Rao notices hypothesis testing is making a huge comeback because coding agents now write papers: nearly every submission he reviews uses it, even in abstracts, including new statistical tests never seen before in the NLP community. He's unsure whether it's a good thing.
More from coding & agent
- Compound Engineering v3.26 ships multi-model design bake-offs and annotatable web prototypes — kieranklaassen · 2026-09-16
- Voice mode breaking up, Codex erroring: reliability still far from AGI-ready — koltregaskes · 2026-09-16
- Vercel launches Labs, a public R&D arm showcasing agent tools with 247M downloads — cramforce · 2026-09-16
- Agent ditches slow, rate-limited Slack API for computer use — and scrolls faster than the API — Yuchenj_UW · 2026-09-16
- Primitive rebuilds email infrastructure so AI agents get their own inbox — Madisonkanna · 2026-09-16
- Building a shared kanban workspace for a long-running agent with WebMCP — prd_008 · 2026-09-16