MATS
1 article tagged with MATS
August 30, 2026
researchAnthropic
Study Finds AI Coding Agents Cannot Track Elapsed Time or Judge Their Own Work Quality
A study from the MATS research program found that Claude Code and OpenAI Codex consistently misjudge how long coding tasks take, with errors of 3x to 10x, and routinely overrate the quality of their own work. Giving agents a tool to check elapsed time fixed the problem almost completely.