The thing I think is underspoken in this space is that LLMs will always hallucinate a bit. How will you know as a 13 year old that an LLM is not conversing truth at you?

▲

hparadiz an hour ago | parent [-]

My teachers were frequently wrong too and spoke with authority on subjects in hindsight they were frankly ill equipped to teach. Part of learning is understanding how to reason through these types of issues. It's a common problem solving problem in the work place just the same.

▲

beepbooptheory an hour ago | parent [-]

Yeah but the teacher says you're wrong even if you're right. The AI tells you you're right either way. The former can facilitate an important lesson, the latter doesn't ever give you the chance to.

▲

hparadiz 40 minutes ago | parent [-]

I've been doing things like accounting where I upload receipts and have the LLM adjust a Google sheet with the money balances. The error rate over the past year has dropped from occasionally to never. That is because there's sub agents now running that check the work. If you have multiple LLMs running with a 94% success rate but you throw them into a group that requires a consensus suddenly the number basically hits 99%.

	▲	beepbooptheory 34 minutes ago \| parent [-]
		We simply need to run sub agents on the children's learning, then we will maximize pedagogic efficiency to 99%.