VP of engineering: coding models report like bad direct reports — raw dumps, no TLDR
robleclerc · x · 2026-11-20
Rob Leclerc critiques coding-model interaction with an analogy: as a VP of engineering in weekly syncs, you expect structured TLDRs with context and decisions from reports — instead you get step-by-step dumps of everything they did, complete with private nomenclature chain-of-thought and missing context.
That, he says, is exactly what interacting with coding models feels like: "it's broken and turns my brain to mush trying to fight it." A sharp take on the missing summarization and context-compression layer in agent output.
More from coding & agent
- Kylon launches AI finance agents that paid $233K in supplier bills over four months — ying11231 · 2026-11-20
- TestSprite 4.0 launches as an independent test layer for AI-written code — Tegadesigns · 2026-11-20
- Dev builds video highlight feature with Gemini Neon, says Claude Opus 5.5 still wins on coding speed — vista8 · 2026-11-20
- Lawyer runs full DeepSeek-V4.1-Flash on 12x V100 at 157-184 tok/s, beating DGX Spark stacks — TumbleweedNew6515 · 2026-11-20
- GitHub open-sources Agent Host Protocol for cross-device agent sessions — rseroter · 2026-11-20
- 100% code-driven Blender squirrel film, made for $34.76 — no video gen models — dreamwieber · 2026-11-20