But, I agree, this is mostly a puff piece. Nothing necessarily wrong with that but not what I would have expected given the other blog posts that have shown up here on HN.
https://blog.exe.dev/inventory for what tools they have. https://blog.exe.dev/botiquette for rules-of-the-road for LLM expectations, my favorite llm rules that i've ever seen. https://blog.exe.dev/exe-scroll for how they use multiple libghostty instances for their web interface.
https://blog.exe.dev/devtools-must-be-open-source got traction recently & is incredible. incredible incredible posting. a spiritual arrow aimed straight at the heart of the agentic age. https://news.ycombinator.com/item?id=49156111
this post is, to me, at least 80% content, 20% pitch. it is extremely good orientation & alignment, gratis. me? i'm incredibly thankful, for this as a waypost, that no one has written down before. a clearly stated beautiful indicator for a massive tectonic shift in software. people being a bit small, if they can't see the incredible value of this post.
Is reviewing endless reams of AI slop something that's doable? It's a very tiring task when you're looking through code that exhibits most of the usual good quality signs -- except it's just a facade that's likely full of subtle mistakes and you barely know the codebase in the first place. I don't think most devs would be particularly happy about having to do it day in and day out, and you definitely can't outsource such work to some bargain bin shop full of clueless people.
Steering an AI, that's doable, especially at a high level. You probably have a rough idea of how you'd approach a given problem, and a wild mismatch between what you'd expect and what's happening is easy to detect. I'm not sure how a human gets into the loop with "light editing" without just telling the clanker to rework X because flamegraph looks unhappy about this part. Any alternatives would probably slow the process down significantly, at which point you might as well write it yourself.