The October 6 Stack Overflow developer survey has a number that settles an argument I keep having on Tuesday afternoons:...

The October 6 Stack Overflow developer survey has a number that settles an argument I keep having on Tuesday afternoons:Write code with AI where you can check the result fast.Pull AI back where checking is expensive.That is not a slogan. It is the survey compressed into one rule. Here are the numbers.67% use AI to generate code in areas they already know well61% use AI to debug20% use AI for production: deploy, operate, troubleshoot78.7% say knowing the source matters to whether they trust an answer6.6% trust AI for important decisions48% trust AI only when they can verify it themselvesRead the top and bottom together. Adoption is not the story. The boundary is the story. Developers trust an agent exactly as far as they can inspect its work. The 20% ceiling is the useful numberThe 67% figure gets all the attention. The 20% figure is the one that should drive your design.Generating code in a domain you already know has a property AI does not need to supply: you can see the error when th...