Yup. I can expect an llm to write proper code to update an hashmap or update a db, but ffs the amount of race conditions, use after free and general concurrency issues I found on colleagues PRs developed fully with these things is disgusting.
You know also what was the biggest help for these companies? All the data they scrapped from the internet, the books they torrented, the open source projects whose licenses they did not respect.
The least these companies can do is to publish everything they own
Well if it's moral for gatekeepers of talent to hoard immense intellectual rights to be protected by the violence of the state, then I'm immoral in that sense. Information wants to be free
I worked with mid level devs that would write 5 lines of code (literally) and run it through an llm for validation, so yeah they were spending tokens like crazy. They end up being more expensive to the company with no added benefit
Exactly. At my previous work we spent an awful amount of time planning and architecting the solutions and refining them. No matter the person who prompted or the model used, the solution was never close to satisfactory.
Layers of unnecessary abstraction, weird decisions (like wth it used triple pointers once) hard to debug issues and obvious race conditions. Segfaults are through the roof and people are burned out and gasping hard to solve the bugs. I called their attention to this at the time and I was ignored and a bit laughed about. I left and couple months later I know others are too.
