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.
More from coding & agent
- Together AI and Ollama explain how prefix caching keeps long agent sessions fast — togethercompute · 2026-11-17
- Recreating The Godfather's office scene with MiniMax H3 in ComfyUI: 3 shots, 37s — hucun16 · 2026-11-17
- Engineer's 2026 job: feeding useful tweets to your agent; Artifacts repos now test locally — itsOmSarraf_ · 2026-11-17
- OpenAI to host NYC hardware hackathon: build working prototypes with Codex in one afternoon — OpenAIDevs · 2026-11-17
- Jeremy Howard reimplements MIT's Recursive Language Models paper inside SolveIt, more concise than original — jeremyphoward · 2026-11-17
- SolveIt internals: persistent server where your Python functions become AI-callable tools — jeremyphoward · 2026-11-17