Agent Distraction

T1Covered by 1 source · first reported by Google — The Keyword / AI / Research / DeepMind / Developers at 06 Nov, 16:33 UTC

Analysis of over 913,000 coding agent sessions reveals that 13% expose agents to inline TODO(b/...) comments. In 6% of encounters, agents act on these comments, with 83% being entirely unprompted by the developer. These detours result in significant overhead—adding 70% more steps, 77% more tokens…

Sources

• T1Agent DistractionGoogle — The Keyword / AI / Research / DeepMind / Developers06 Nov, 16:33