If your evals can't block a merge, they're decoration
bgoncalves · x · 2026-10-01
Reacting to the hot take that LLM apps without a CI eval gate leave you not knowing if they work, developer bgoncalves goes further: evals that can't block a merge are decoration. LLM quality assurance must be a hard gate in CI, not manual spot checks.
More from coding & agent
- PivotOPD: NVIDIA Paper Teaches Multi-Turn Agents to Recover From Early Pivotal Mistakes — MohitIyyer · 2026-10-01
- Overmind open-sources a platform that fine-tunes agents from production traces — kimmonismus · 2026-10-01
- Dev turns Cloudflare birthday-week blog flood into Claude prompts — threepointone · 2026-10-01
- Fable 5.1 vibe check: stronger coding, half the tokens of Opus 5, and it finally talks like a person — every · 2026-10-01
- All Three Labs Shipped Frontier Models in 10 Days — How Do You Pick One for Production? — Sur_AI_guy · 2026-10-01
- Zapier CEO grades three levels of AI-powered PM work live, top level is a full agent operating model — aakashgupta · 2026-10-01