Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop.

Added to korrents 7 Jun 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. MZMario Zechner25 Mar 2026similar wording
• The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. ESElizabeth Stone19 Jul 2026similar wording
• Whether agent-written code needs to be good depends entirely on how long it will live: a throwaway single-page tool can be spaghetti, anything maintained cannot. SWSimon Willison19 Mar 2026similar wording
• Writing code with a coding agent and no tests at all is indefensible, because the old objection to testing — that it is extra work you then have to maintain — no longer applies. SWSimon Willison19 Mar 2026similar wording
• A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would. SWSimon Willison19 Mar 2026similar wording

See this on the map →