Post #1766108

2026-04-28 16:29 UTC

I support a call center and we’re about to implement an AI agent. We’re paying for a model that essentially can talk and has “learned how to learn”, but is otherwise dumb. It’s trained on a very small amount of information, anything we’d give to a real agent, plus the public info on our website. The result of this should be a bot that says, “I don’t know, should I transfer you to a real person?” a lot, but should hopefully never hallucinate or teach someone how to build a bomb or something. Dunno how others do it though

Replies (6)

@0_o7@lemmy.dbzer0.com 2026-04-29 06:06

The one you’re using isn’t probably a wrapper around OpenAI or other cloud based API, the ones that are misconfigured are more prone to these types of abuse.

Open ##1766107
@null@piefed.nullspace.lol 2026-04-28 17:09

Those kinds of bots work fine these days.

Open ##1801682
@TachyonTele@piefed.social 2026-04-28 17:29

That’s the kind of system set up that makes sense

Open ##1801953
@HeyThisIsntTheYMCA@lemmy.world 2026-04-28 17:47

hopefully never hallucinate or teach someone how to build a bomb or something. that’s so fucking easy you just lick toads until you find the right one who needs to go to the internet for that.

Open ##1801987
@WoodScientist@lemmy.world 2026-04-28 21:21

The result of this should be a bot that says, “I don’t know, should I transfer you to a real person?” a lot, but should hopefully never hallucinate or teach someone how to build a bomb or something. This is in contrast for the AI agent for my company, whose customer service number is 1-800-BLD-A-BMB.

Open ##1804426
@Steve@startrek.website 2026-04-28 20:56

I have never seen a chatbot say “i dont know”

Open ##1806832