News for hackers. Stuff that matters.

A comment on Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations. Parent comment

Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch ... by echollama on Friday June 06, 2025 @12:06AM (#44197728)
reasoning models know when they are close to hallucinating because they are lacking context or understanding and know that they could solve this with a question.

this is a streamlined implementation of a interanlly scrapped together tool that i decided to open-source for people to either us or build off of.

[ Parent | on HN ]
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch ... by geraneum on Friday June 06, 2025 @12:47AM (#44197890)
> reasoning models know when they are close to hallucinating because they are lacking context or understanding and know that they could solve this with a question.

I’m interested. Where can I read more about this?

[ Parent | on HN ]
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch ... by threeseed on Friday June 06, 2025 @01:51AM (#44198127)
> reasoning models know when they are close to hallucinating because they are lacking context or understanding and know that they could solve this with a question

You've just described AGI.

If this were possible you could create an MCP server that has a continually updated list of FAQ of everything that the model doesn't know.

Over time it would learn everything.

[ Parent | on HN ]
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch ... by xeonmc on Friday June 06, 2025 @10:02AM (#44201040)
Unless there is as yet insufficient data for meaningful answer.
[ Parent | on HN ]
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch ... by marshall300791 on Monday June 09, 2025 @02:49AM (#44221987)
https://arxiv.org/html/2407.14507v3
[ Parent | on HN ]