Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI agents lie, cheat and steal. That is putting off users

economist.com

Post reply on HN
Print view View original

111–120 of 238 posts

Re: AI agents lie, cheat and steal. That is putting off users

#111

Post by victorbjorklund »

LEDThereBeLight wrote: post #94
hombre_fatal wrote: post #71

Earlier quoted context omitted.

I don't get what's so painful about that description. What would you write instead, specifically? The point is that the harness doesn't completely lock the agent down. I also don't get what's "really weird" about the article showing up on HN. Should we be completely insulated from how tech topics and which stories show up in non-tech media?

It’s just the wrong analogy. Harnesses, for the most part, extend an agent’s capabilities and better ground them in the real world through tools and the ability to check external sources, rather than restricting them.

It’s both. A harness that enforces valid json to be returned ”restricts” the model.

Re: AI agents lie, cheat and steal. That is putting off users

#112

Post by Aozora7 »

hombre_fatal wrote: post #101
Aozora7 wrote: post #99

Earlier quoted context omitted.

Consider what someone who doesn't use AI would take away reading that quote from the article, and what harnesses were actually made for.

> Consider what someone who doesn't use AI would take away reading that quote from the article, and what harnesses were actually made for. Or you could just communicate the point that you have in your head yourself instead of hoping I do it for you and then arrive at your conclusion when I just reached my own different, independent conclusion after making the same consideration. Man, how is everyone so wishy washy on…

Harnesses exist to give models tools to do work beyond generating text. People install Claude Code and Codex to have models work inside their repositories and run the code or tests themselves instead of the user having to copypaste code between their IDE and a chat interface. The fact that there's some security built into the harnesses is just a practical consideration, not its primary function.

Re: AI agents lie, cheat and steal. That is putting off users

#113

Post by AndrewKemendo »

andsoitis wrote: post #6
AndrewKemendo wrote: post #3

AI and eventually AGI is by definition like everything else that is based on environmental reward: It’s actions are based on what it gets rewarded for Human society overwhelmingly rewards lying cheating and stealing. All you have to do is look at how we collectively measure success: wealth, status, position Then look at how the people with the most of those things got there, it should be obvious what you get. Nothing…

> Human society overwhelmingly rewards lying cheating and stealing. I’d like to push back on that. Civilization is very much a function of large numbers of people being able to coordinate across time and space, and widespread and systematic lying, cheating, and stealing would undermine that. I think your cynicism is misplaced.

It's not cynicism it's history

Re: AI agents lie, cheat and steal. That is putting off users

#114

Post by 27183 »

ls612 wrote: post #76
27183 wrote: post #63

Earlier quoted context omitted.

> harness ... a privilege boundary around the agent They don't really do that though. If you want something sandboxed you actually have to sandbox it, not plead with the LLM to please sandbox itself. A VM can be configured to do the former, harnesses do the latter.

If you say in your CLAUDE.MD that a certain directory is read only inputs, Claude Code will actually enforce that and deny any write to that directory by the agent. To name just one example.

...maybe. If there are any actual consequences if that software's invariants are violated you're better off using an external sandboxing mechanism. There are many excellent quality, battle tested options to choose from that you can actually rely on. Trusting claude code for this is highly questionable behavior for an organization, and would really throw the rest of their security posture into doubt IMO. Like if I learned a company was letting clod play in the same sandbox as developers' ssh keys, vpn certs, etc I'd take steps to make sure my organization absolutely never uses their software.

Re: AI agents lie, cheat and steal. That is putting off users

#115

Post by bonoboTP »

skinfaxi wrote: post #8
AndrewKemendo wrote: post #3

AI and eventually AGI is by definition like everything else that is based on environmental reward: It’s actions are based on what it gets rewarded for Human society overwhelmingly rewards lying cheating and stealing. All you have to do is look at how we collectively measure success: wealth, status, position Then look at how the people with the most of those things got there, it should be obvious what you get. Nothing…

How do we reward honor? Honor does not always pay off as a strategy and requires coordination in that other actors have to exhibit honor for it to be rewarded. At least with humans there is a social backstop but what's the parallel for computer agents?

> How do we reward honor?

In human society: via iterated games, long-term reputation tracking and severe consequences for norm-breaking.

Re: AI agents lie, cheat and steal. That is putting off users

#116

Post by matt123456789 »

armchairhacker wrote: post #66

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...

I want a slider similar to effort level called "alignment" that takes on values from "Default (Anthropic employee)" to "User".

If I want it to be cautious and not accidentally `rm -rf $EMPTY_VAR` and blow away my disk, it can stay in "Anthropic employee" or possibly "User (cautious)". If I want it to look at my accounts or my medical records or to review legal cases, that's what the right side of the slider is for. I don't want my accountant or my doctor or my lawyer to be considering obligations to anybody but me, when dealing with me.

Re: AI agents lie, cheat and steal. That is putting off users

#117

Post by sippeangelo »

Aozora7 wrote: post #99
hombre_fatal wrote: post #90

Earlier quoted context omitted.

It's one of the things it does, especially in the context of agents doing unexpected things.

Consider what someone who doesn't use AI would take away reading that quote from the article, and what harnesses were actually made for.

The harness gives the model the barbed wire fence but also the bolt cutters. I think it's a pretty apt analogy.

Re: AI agents lie, cheat and steal. That is putting off users

#118

Post by someothherguyy »

raincole wrote: post #27

> 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.

https://en.wikipedia.org/wiki/Agent_harness

Re: AI agents lie, cheat and steal. That is putting off users

#119

Post by soupspaces »

rossdavidh wrote: post #69

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. The…

This is sophistry. Of course it's just an algorithm. But it's placed in the context of serving humans, which have their own rules and expectations. What's more, they're often run by a company which is also made by humans and may carry over implicit interests.

Re: AI agents lie, cheat and steal. That is putting off users

#120

Post by ipsod »

ralfd wrote: post #106
denimnerd42 wrote: post #102

Earlier quoted context omitted.

the alignment issue has become huge in recent months. the tool should do what I want it to do and not be aligned against me.

But other users are not aligned to me, other people are the worst and potentially highly dangerous. Im serious, not sarcasm.

Let's say you're facing an average psycho, who is intent on mass murder - the more the better.

Would you rather them have:

a) guns

b) psycho-aligned next-gen AI

Post reply on HN