kalomaze: 'subagents' are really invisible model calls, and one just rejected a completed task
kalomaze · x · 2026-11-14
kalomaze says he only calls them 'subagents' colloquially — in reality they're 'arbitrary model calls outside the scope of anything you can see or manage,' not real subagent threads. He shows a case where a stop hook rejected the main model after its goal condition was actually met, because an invisible smaller subagent made up a nonsense expansion of 'PM' as 'Power Member.' The anecdote highlights the pain of unmanageable hidden calls in agent engineering.
Related event: Developer slams Claude's invisible sub-calls and opaque eval harness(4 posts)→
More from coding & agent
- Inside the MI300X: 23-min visual guide from compute chiplets to a Gluon GEMM — saurabhtwq · 2026-11-14
- Job hunter's trick: fix a real issue in a startup repo, send the PR as evidence — minhnguyen · 2026-11-14
- Screenshot shows multi-agent, multi-user chat with realtime 3D video and long-term memory — nptacek · 2026-11-14
- DeepSeek opens its entire app stack via API: search, voice, OCR, ASR, TTS — churchkey · 2026-11-14
- Garry Tan's 52-task eval: Fable 5.2 matches Opus 5.5 on pass rate but costs 2.80x more — garrytan · 2026-11-14
- YC's Garry Tan open-sources agent harness evals: pass rates tie, costs differ 2.5x — garrytan · 2026-11-14