I sometimes have that feeling too, then ask another LLM to do a code and vulnerability review and OMG: rookie mistakes, over complications and security gaps even a 1st year student would not make regularly.

So.. one more year of untreated bipolar AI psychosis I guess..

▲

chpatrick 14 hours ago | parent | next [-]

I think these kinds of comments really need to say which LLM that is. There's an enormous difference in skill between the frontier ones and say the Google search AI.

	▲	PedroBatista 6 hours ago \| parent [-]
		Codex Luna, Terra and Sol. Claude Opus, Sonnet and sometime Fable. They all work, they all are "good", they all are both "smart" and commit incredible basic mistakes a fair amount of times. Then there's the cost situation..

▲

brokencode 4 hours ago | parent | prev [-]

At least we are at a point where we can have AI review code and reliably find real problems. That alone is incredibly valuable.