logoalt Hacker News

lionkor • yesterday at 1:10 PM • 0 replies • view on HN

You're implying that GPT-6 Sol can do better. That is not how LLMs work! They will write code, and then, in a separate invocation, find 100 problems with that code. Unlike humans, the immediate context massively impacts the immediate next response, and "knowing better" is nearly entirely irrelevant, because even with thinking and reasoning, these machines do not adequately reflect.

Instructing them to reflect also doesn't help; they pull whatever hallucinations make up the "reflection" into immediate context, and now they're even more confused.