Sentry CEO vs Anthropic engineer: should you build your own coding harness?
pvncher · x · 2026-10-06
Sentry CEO David Cramer (@zeeg) argues lab-provided coding harnesses are often not best-in-class, and as developers shift to open models, locked-down harnesses will stifle innovation—compaction alone isn't a solved problem. Anthropic's @pvncher pushes back: models increasingly specialize around their native harnesses, so minor efficiency tweaks may not pay off, and custom evals likely aren't general-purpose enough to catch regressions elsewhere. His advice: skip the one-size-fits-all harness and build your layer on top of each provider's native harness instead.
Related event: Agent harness tier list sparks debate over compaction and vendor lock-in(12 posts)→
More from coding & agent
- Matt Shumer builds Hogwarts live on Spawn with AI in a multiplayer world — mattshumer_ · 2026-10-06
- Ruff author shares build-speed trick: one crate per file for faster compiles — charliermarsh · 2026-10-06
- Notable MCP critic converts, now wants an official Gmail MCP — zeeg · 2026-10-06
- Developer Runs 1,200+ Blender Modeling Sessions to Blind-Rank LLMs and Agent Harnesses — Izolight · 2026-10-06
- Software-in-the-loop: self-supervised scaling of terminal environments lifts Terminal-Bench 2 to 53.56% — Zhongzhi Li · 2026-10-06
- Real product photos plus LTX-2.5 rotation videos and Codex-coded UI rebuild a brand demo — OpenAIDevs · 2026-10-06