AI is breaking our proxies for expertise
The signals we used to judge competence — clean code, fast output — no longer carry information.
A link and why it matters. Two sentences, no more.
The signals we used to judge competence — clean code, fast output — no longer carry information.
The clearest public writing on when an agent loop beats a fixed workflow.
An argument that agents should use the tools humans already use, rather than getting bespoke ones.
On treating low-quality agent output as an engineering problem rather than a model problem.
A long thread of the posts that actually changed how working engineers think.
If the model is faster than your CI, your CI is now the product constraint.