I think that this looks like a great tool, that I'd use (and that I'd want for other languages, tbh)
The current ai-coding hype is already losing some steam as a lot of people are realising that the generated code is of dubious quality and requires (overall) more time for anything other than a one-shot "it's good enough" project. Sadly, people will use this for an MVP - which we all know, _doesn't_ get thrown away, but becomes production code at some point, when someone will have to maintain it.
Personally, I don't use any of these "assistants" as I find them way more annoying than useful - filling in obviously incorrect code, or, worse, subtly buggy code. Every demo I've been at, once the speaker has triumphantly shown the results of new tool X, I've found an issue with the code - more often than not, an actual bug where the code doesn't meet the requirements specified in the prompt.
"vibe-coding" (what a cringe term) will (imo) soon distinguish marginally-skilled programmers (who use these tools) from proficient ones (who have to clean up the mess).
With AI-assisted coding on the rise, I'm starting to wonder if humans will still need code search tools, or if generative models will do it all for us. On the other hand, maybe code search will become even more critical, especially as AI-generated codebases balloon and eventually need thorough refactoring, security audits, or just plain manual debugging.
Context: A friend wrote a semantic code search tool (syng.dev) designed for developers maintaining large or legacy codebases, or for web security folks. It's great, but I'm unsure about how demand might shift if coding becomes more "AI-first." That said, I could see these tools being just as useful (if not more so) for the AI agents themselves when sifting through massive amounts of code.
What do you think? Does code search still have a bright future, whether for humans or AI, or is it fated to become obsolete in the era of "vibe coding"?
The current ai-coding hype is already losing some steam as a lot of people are realising that the generated code is of dubious quality and requires (overall) more time for anything other than a one-shot "it's good enough" project. Sadly, people will use this for an MVP - which we all know, _doesn't_ get thrown away, but becomes production code at some point, when someone will have to maintain it.
Personally, I don't use any of these "assistants" as I find them way more annoying than useful - filling in obviously incorrect code, or, worse, subtly buggy code. Every demo I've been at, once the speaker has triumphantly shown the results of new tool X, I've found an issue with the code - more often than not, an actual bug where the code doesn't meet the requirements specified in the prompt.
"vibe-coding" (what a cringe term) will (imo) soon distinguish marginally-skilled programmers (who use these tools) from proficient ones (who have to clean up the mess).