Yoav Goldberg: Claude Code's harness barely matters — code quality comes from the LLM
yoavgo · x · 2026-11-18
Responding to concerns that Claude Code is being used to write a significant fraction of new software without people understanding its details, Yoav Goldberg argues the software-writing component is the LLM itself: bugs stem from the model, and Claude Code's own TUI and harness have very little effect on the quality of the produced code.
More from coding & agent
- Code Mode turns 1: every major agent harness has adopted it — and kept the name — ritakozlov · 2026-11-18
- GitHub and Microsoft's MDASH pilot turns thousands of AI vuln findings into 99 verified fixes — mustafasuleyman · 2026-11-18
- OpenAI updates API dashboard with per-model usage, rate-limit and error tracking — OpenAIDevs · 2026-11-18
- 'Proof-Carrying Calls' Idea: Make Agents Certify They Don't Break Your Invariants — tianyin_xu · 2026-11-18
- Devin Platform Adds a 'Poke' Bot Template: An Engineering Agent with Personality — marvinvonhagen · 2026-11-18
- Carbon TTFT now 1.5x faster on Antigravity, Argon to follow — cgarciae88 · 2026-11-18