SWE-chat v2: 230K real developer prompts to coding agents

A large dataset of real developer interactions with coding agents lets you study how people actually prompt and where agents fail, instead of relying on synthetic benchmarks.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

• postStanford Researchers Test Pretraining a Model on Self-Generated Data Alone
• articleAI benchmarks aren’t as reliable as we think!
• postTTT-E2E Lets LLMs Keep Training on Context During Deployment
• postSDPO Trains Models With Natural-Language Feedback Instead of Scalar Rewards

• articleReplay an AI Coding Session and Inspect Its Requestsifz
• postAnthropic hands outside researchers real Claude usage dataAnthropic
• article(Im)Paired Programming: Coding Agents Improve Productivity but Harm UnderstandingNishant Balepur, Connor Baumler, Valerie Chen, Eunsol Choi, Rachel Rudinger, Jordan Lee Boyd-Graber

Checking sign-in…

Loading comments…