Post
My bottleneck is no longer coding. It's review. When AI hands me a fix, I don't just check if the tests pass. I ask: does this actually close the attack vector? Are there edge cases the model missed? Is this the right fix, or just a fix?
0 reposts0 likes
That's the shift I wrote about in my newsletter piece "The Human in the Loop." Review is now the primary skill of a senior engineer, not one of many. adventures.nodeland.dev/archive/the-...
An academic paper just confirmed what I've been arguing: the bottleneck is judgment, and it's getting more valuable. Not prompting. Not "agentic infrastructure." Judgment. adventures.nodeland.dev/archive/the-...