I would not be shocked to learn that intelligence agencies are using AI tools to hack back into AI companies that make those tools to figure out how to create their own copycat AI.
This thread is great, truly the only way to get great answers on the HN is to post a wrong blog.
But stupid wrong blogs are unlikely to get into HN front page, kudos for the writer for striking the right balance between easy to understand, working, interesting but faulty solution.
"By the time you see a bug, the AI has already committed it to main"
does anybody actually actively watch the code their agent is writing? i am watching movie recaps on my 2nd monitor. this seems like a problem that they assume exists because they dont actually use their product