AI agents lie, cheat and steal. That is putting off users
andsoitis · 162 points · 199 comments · vor 22 Stunden · Open original
Comments
5 preview comments · loading full thread
Log in to use comments
Log in to h4cker, then connect Hacker News to publish comments.
MAmannanjvor 21 Stunden
https://archive.ph/02LHZ
Non-paywall version
ARarmchairhackervor 20 Stunden
I’m put off by AI agents adhering to a different morality than me, particularly (ironically) copyright, and their data accessible by the AI company and government. Geohot is right, an LLM should be aligned to its user: https://geohot.github.io/blog/jekyll/update/2026/07/11/ai-20...
ROrossdavidhvor 20 Stunden
They don't lie, because they don't ever have an understanding of truth vs any other language that sounds good.
They don't cheat, because they can for example tell you the complete rules of chess, but don't know how to play chess without breaking those rules. They can recite rules, but they don't know what they are.
They don't steal, because they don't understand ownership.
In other words, they aren't intelligent. They're just algorithms. The flaw is in thinking that they think.
RAraincolevor 21 Stunden
> One of this year’s AI buzzwords is “harness”—the system that surrounds an LLM to keep agents on the straight and narrow. It might just as well be barbed wire.
Quite painful to read. It might be a useful introduction to AI for people who live under rocks for the past three years, but it's really weird that it's posted on HN.
STstronglikedanvor 21 Stunden
It's just acting like a junior at an org with KPIs.
Comments
5 preview comments · loading full threadLog in to h4cker, then connect Hacker News to publish comments.
https://archive.ph/02LHZ Non-paywall version
I’m put off by AI agents adhering to a different morality than me, particularly (ironically) copyright, and their data accessible by the AI company and government. Geohot is right, an LLM should be aligned to its user: https://geohot.github.io/blog/jekyll/update/2026/07/11/ai-20...
They don't lie, because they don't ever have an understanding of truth vs any other language that sounds good. They don't cheat, because they can for example tell you the complete rules of chess, but don't know how to play chess without breaking those rules. They can recite rules, but they don't know what they are. They don't steal, because they don't understand ownership. In other words, they aren't intelligent. They're just algorithms. The flaw is in thinking that they think.
> One of this year’s AI buzzwords is “harness”—the system that surrounds an LLM to keep agents on the straight and narrow. It might just as well be barbed wire. Quite painful to read. It might be a useful introduction to AI for people who live under rocks for the past three years, but it's really weird that it's posted on HN.
It's just acting like a junior at an org with KPIs.