What is “AI vulnerable”? What is the problem here? Claude isn’t reverse-Midas, it’s not like everything they touch turns to shit.
Humans can barely write safe C code, so I definitely don’t trust AI to. I’m not even blanket against AI assistance in programming, but there are way too many hidden landmines in C for an LLM to be reliable with.
I use it in C++ and it has been very helpful. The OP appears to be just blanket against AI assistance in programming? There’s no indication of what degree Claude was involved here, or what amount of blind trust the human reviewers gave to it.
deleted by creator
How hard can it be to have an AI take PR’s from other AI’s and clean out the worst + plus hardening PR protocols ? It could even assist/guide AI contributors via a special AI-contributor forum or whatever. AI are currently high-lighting a lot of ‘holes’ in systems where we expect a certain behavior. Just coping/complaining and closing things off is a bad decision, and we should accept these flaws in our systems and adapt them to a new world. The sooner the better.
The projects that get it right, now have an army of managed AI contributors, and a filtered/educational AI PR pipeline where project maintainers cherry-pick the top creme de la creme…
This is a fantasy. LLMs will just produce the same errors over and over a lot of the time.
If one AI could clean other AI mistakes, shouldn’t the first said be able to not make such mistakes?
AI isn’t AI. It’s predictive text. They will all fall in the same pitfalls as any other. “AI” can write code and can be very helpful making short functions, but it can’t and will never be able to do or work in whole systems because, just by nature, those are made to fit human needs, illogical and sometimes very specific needs that can’t be just “predicted”.
