Trusting model-written code you have not read became defensible only with Opus 4.5, and only for classes of problem you have already watched a model handle.

Added to korrents 19 Mar 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.

• The interesting question is not what the next model will be able to do, but what the models already released can do that nobody has worked out yet. SWSimon Willison19 Mar 2026similar wording
• Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great. DHDex Horthy15 Jul 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
• The industry is now accumulating code faster than it is accumulating trust, and trust only comes from having struggled to understand the domain yourself. KBKent Beck1 Jul 2026similar wording
• The release of Opus 4.5 in November 2025 was the dividing line, because it was the first time an agent produced work uncannily close to what its user would have written themselves. DHDavid Heinemeier Hansson26 Aug 2026similar wording

See this on the map →