Our readingWhat is a korrent?
In most domains agents are now better than humans at finding bugs.
Drawn from what David Heinemeier Hansson said
Our readingWhat is a korrent?
Drawn from what David Heinemeier Hansson said
And this was with models we had six months ago. At this point, 100% in the majority of domains we work in today, agents are better at finding bugs.
Added to korrents 30 Aug 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooIn tension with
Hansson’s argument for keeping junior programmers is that someone must be able to vet what the machine produces. Sixteen months later he holds that the machine is better at that vetting than the humans are. The conclusion can survive — juniors become seniors, and that pipeline has other justifications — but the reason he gave for it does not.
In tension with
Hansson says agents are now better than humans at finding bugs in most domains. Zechner says the tests an agent writes for agent-written code are as untrustworthy as the code, and that manually using the product is the only reliable measure left. Better at finding bugs and unable to certify its own work are compatible, and the gap is exactly where a team decides how much to review.
Shared subject first, then similar wording. They may agree or disagree.