I use ChatGPT to give me overview of some unfamiliar topics, suggest some architecture patterns, learn about common approach to solve X or refresh on some syntax. Sometimes there’s a repetitive task like applying same edit to a list of like 40 strings (e.g. surrounding them in struct init), and I found it useful to make ChatGPT do this. Summarising diffs in openapi, highlighting bugs and patterns in logs, documents also works pretty okay.

In my domain (signal processing, high load systems, embedded development, backend in Go) it doesn’t do great for coding tasks, and I’m very opposed to giving it lead to create files, do mass edits, et cetera. I found it to fail even on recent versions of Go, imagining interfaces, not knowing changes in some library interfaces (pre-2024 changes at least). Both ChatGPT and Claude failed to create proper application for me (parsing incoming messages and drawing real time graphics), both getting stucked at some point. Application worked more or less, but with bugs and huge performance issues.

I found it useful to quickly create skeletons for scripts/tools, that I can then fill up with actual logic, or making example of how a library is used.

So there is usability for me, it replaced stackoverflow and sometimes reading actual documentation.

I own a few repositories of our system, and contribution guides I create explicitly forbid use of LLMs and agents to create PRs. I had some experience with developers submitting vibe coded PRs and I do not want to waste my time on them anymore.