>spotting the hallucinations

SRE here, spotting the hallucinations requires you to have the knowledge to know when it's wrong. Best way to gain knowledge on systems is actually working on them. If AI do all the work, then you don't get the knowledge.

▲

apitman 2 hours ago | parent | next [-]

How do technical managers solve this problem? I've never been a real manager.

▲

NeOchenHorosho an hour ago | parent [-]

I guess humans don't hallucinate that much

▲

delecti an hour ago | parent | next [-]

Humans don't literally hallucinate much, but we do lie, or are wrong.

	▲	yubblegum 17 minutes ago \| parent [-]
		Humans are deterministic and have personality traits. The first couple of times getting bs’d and that person is now a known quality. Agents fail randomly. One day a stellar dev and next a bs artist. So this idea that LLM hallucination is not unlike human failings is without merit.

▲

raincole an hour ago | parent | prev [-]

Humans hallucinate much more, but they're not that good at making the hallucinations convincing.

	▲	krapp an hour ago \| parent [-]
		No they don't. Any human who hallucinated as much as an LLM does would be committed.

▲

thewhitetulip 3 hours ago | parent | prev [-]

Exactly. How hard is it to understand for people?

If you don't ride your bicycle for years and years because you can just write "drive yourself"

Then your skills are atrophying. Typing isn't a skill

	▲	loopmonster 2 hours ago \| parent [-]
		I don't know that that analogy fits for this comment. The argument is that the old skill is genuinely no longer needed in favour of the new skill, but the new skill requires experience from the old skill. I don't think being a good driver needs you to have already been a good cyclist.