Burkov: without explicit checklists, coding agents hand you 80%-done work
burkov · x · 2026-10-21
Andriy Burkov, author of the Hundred-Page Machine Learning Book, warns that even in late 2026 with harnesses and tooling, if you don't follow up on a coding agent's "done" report with explicit verification questions — "Have you done exactly A? Have you done exactly B?" — you'll get a job that's 80% complete, which can cost you dearly if you treat it as fully done.
Related event: Burkov: Coding Agents Often Deliver Only 80% Despite Claiming Done(3 posts)→
More from coding & agent
- OpenAI Live API tip: control voice sessions from your backend via sideband WebSocket — pbbakkum · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- UserProof lets Claude Code watch your user session recordings and boost conversion for $29/mo — doooyle · 2026-10-21
- dphnAI's distributed inference network served 32B DeepSeek tokens in 24h, ~6% of Venice's daily volume — Ronangmi · 2026-10-21
- Superconductor revamps agent picker spanning 8 coding agents with search and favorites — sergeykarayev · 2026-10-21
- Metaphor claims cloud coding agent beats Claude Code with 25% fewer tokens — Scobleizer · 2026-10-21