logoalt Hacker News

Archer6621 • today at 9:32 PM • 0 replies • view on HN

That's because LLMs are incoherent by design, and need extensive guardrails to be useful for tasks that demand coherence.

I share a similar experience with bug finding; I think it also helps that LLMs can simply hold much more context at once than a human, as seeing a much larger portion of the codebase simultaneously makes it much easier to spot discrepancies.