Eh, I dunno -- I have an LLM write a feature, then create a PR. Subsequent bot reviews list tons of "problems" (some relevant, others not so much). Why couldn't the first LLM get it right the first time?
Ask your LLM to review the PR before submitting it. Then make it fix the problems. Then repeat the process until there are no more problems. At each step, document where it went wrong in a guide; next time, it can use that guide and will make less errors.
In other words, treat it like a junior that has infinite enthusiasm and talent but zero existing habits or wisdom. If you are not doing something like this, then you are going to have a bad time.
Especially with the recent slew of layoffs in the gaming industry. One anecdotal report from a local small time game dev said they'd get hundreds, if not thousands of responses to an open position, both domestic and international from recently fired game developers.
It's a really weird market, it's both one of the biggest industries in the world (bigger than music and movies combined), yet also high unemployment and poor working conditions / work/life balance, with AI throwing another spanner in the works. Meanwhile a lot of people that want to work in it aren't just in it for the money, they have genuine passion for the craft / industry - which is actually rare in most IT jobs, most enterprise jobs aren't exactly exciting material.
It's still early days, I'm hesitant to claim the death of software engineering. It's good now because LLMs were all trained on actual human output. One possible future is a slop death spiral.
I sure as hell am never again releasing human-authored open-source in a way that can be scraped. My Github is now relegated to the lowest quality slop from the cheapest models.
reply