Seroter's reading list: humanizer skills tested, subagents considered harmful, token waste

rseroter · x · 2026-11-17

Richard Seroter's daily reading list (#910) covers engineering-focused AI pieces: benchmarking 7 "humanizer" skills that strip AI-writing tells; smart forks with context vs. subagents working from summaries; Gemini + constraint solvers catching Go bugs fuzzing misses; coding agents burning two-thirds of tokens after the first edit unless forced to declare a plan; Antigravity /teamwork agent-team case studies; and measuring developer productivity under Goodhart's Law.

Original post →

More from coding & agent

coding & agent channel →