Having an AI agent write tests costs tokens in the short run and saves them in the long run, because the classic failure is that the code does not work.

Added to korrents 1 Jul 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.

• When an AI agent runs out of forward progress, throw the project away and start over rather than trying to tweak it. KBKent Beck1 Jul 2026similar wording
• The case for sweating every line of code was premised on humans doing the modifications, and it now survives only because tokens are scarce. DHDavid Heinemeier Hansson26 Aug 2026similar wording
• 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
• Token prices have stayed flat because labs deliberately kept models smaller than expected in order to get more experimental cycles. RGRyan Greenblatt11 Aug 2026similar wording

See this on the map →