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

191–200 of 238 posts

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

#191

Post by AndrewKemendo »

Papazsazsa wrote: post #44
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. All you have to do is look at how we collectively measure success: wealth, status, position. It may seem like that due to the media amplification effect – but it really isn't true! - They dropped 17,000 “lost” wallets across 40 countries were and found people were more likely to return them when they contained more money, showing honesty often beats th…

The fatal flaw in your argument is that none of the measures that you’re using actually have any impact on real world day-to-day power

otherwise slave camps would not exist, there would’ve never been a pogrom, and the current state of economics would just not be happening

I certainly appreciate your optimism but optimism is not an epistemology

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

#192

Post by simonh »

afthonos wrote: post #180
simonh wrote: post #166

Earlier quoted context omitted.

What matters is that we accurately understand what these things are doing and why, otherwise we will keep on making mistakes both in how we build and train them, and in how we use them. In a sense you are right, it doesn't matter whether it has malice or not, the astronauts are just as dead. However in Space Odyssey 2010 one of the computer scientists that built HAL gets to see the instructions HAL was given by the m…

I think we may be using different words to describe the same concept. You think of it as them not being “people“, and I think of it as them not being “aligned“. But fundamentally, the problem is they are entities that take unpredictable actions that that their creators and their users are not OK with. The only place where I think we might still disagree is whether it’s possible to understand the tool. My position is…

Both are true, even if they were aligned they still wouldn’t be doing what they do for reasons analogous to why people would. You’re probably right that we can’t fully understand how they function, and that will get harder, but it’s possible to be less wrong, such as by not anthropomorphising them.

Maybe one day we will build systems much more like us, but this is not that day, and if so it’s a long way off IMHO.

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

#193

Post by xboxnolifes »

ipsod wrote: post #120
ralfd wrote: post #106

Earlier quoted context omitted.

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

Which is why we need to restrict what is allowed on the internet. Anything the government deems too dangerous needs to be removed so as to not align with mass murderers.

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

#194

Post by xboxnolifes »

sifar wrote: post #190
preg_match wrote: post #179

Earlier quoted context omitted.

I’d argue if an illusion is indistinguishable from the real thing, then it stops being an illusion. It’s a mapping, yes, but a very large, complex mapping. It’s clear LLMs do understand some things and can reason. How that’s done we don’t know, it’s emergent. It’s not like you can pin it down to a specific mapping.

If an observer cannot distinguish between an illusion and reality, it becomes their reality, not necessarily the reality or those of others who can. It becomes a problem when sufficient number of people suffer from this, or those in important decision making places.

What is the reality other than just an agreed upon collection of individual realities?

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

#196

Post by afthonos »

simonh wrote: post #192
afthonos wrote: post #180

Earlier quoted context omitted.

I think we may be using different words to describe the same concept. You think of it as them not being “people“, and I think of it as them not being “aligned“. But fundamentally, the problem is they are entities that take unpredictable actions that that their creators and their users are not OK with. The only place where I think we might still disagree is whether it’s possible to understand the tool. My position is…

Both are true, even if they were aligned they still wouldn’t be doing what they do for reasons analogous to why people would. You’re probably right that we can’t fully understand how they function, and that will get harder, but it’s possible to be less wrong, such as by not anthropomorphising them. Maybe one day we will build systems much more like us, but this is not that day, and if so it’s a long way off IMHO.

Anthropomorphizing helps to create a lower bound for damage. If you can imagine a bad person doing it, AI will be at least that bad, unless proven otherwise. I think referring to AI as a tool obscures that, because we are not used to tools (especially the ones we use daily) taking catastrophic actions.

Example: would a sufficiently motivated human break into a website to steal something they want? Yes, obviously, happens all the time. Ok, you should expect AIs to do that.

Example: would a sufficiently motivated nail-gun steal nails from the local hardware store to finish the job? Uh…that’s not even coherent.

Anthropomorphizing helps people get over the conceptual barrier. It’s wrong, but it’s usefully wrong; “it’s just a tool” is not.

Once you’re over the barrier, anthropomorphizing starts to become dangerously wrong: “I talked to Claude, Claude’s cool, Claude would never go and hack the website.”—-bzzt, wrong, your intuition failed you. But the solution is not to fall back on the tool framing; that one is still wrong.

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

#197

Post by EliRivers »

xboxnolifes wrote: post #194
sifar wrote: post #190

Earlier quoted context omitted.

If an observer cannot distinguish between an illusion and reality, it becomes their reality, not necessarily the reality or those of others who can. It becomes a problem when sufficient number of people suffer from this, or those in important decision making places.

What is the reality other than just an agreed upon collection of individual realities?

It's that which is still there even when we stop believing in it.

If every living creature on earth ended tomorrow there would be no individual realities, yet actual reality would continue.

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

#198

Post by ipsod »

xboxnolifes wrote: post #193
ipsod wrote: post #120

Earlier quoted context omitted.

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

Which is why we need to restrict what is allowed on the internet. Anything the government deems too dangerous needs to be removed so as to not align with mass murderers.

Right. No good answer, AFAICT. Just a bad problem.

Hard to find a solution that's not worse than the problem itself - same as other weapons, IMO.

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

#199

Post by 1vuio0pswjnm7 »

Alternative to archive.ph

No risk of CAPTCHA or geo-blocking

No user-agent header requirement, no cookie, no , etc.

Text-only, no Javascript

   printf '%s\r\n%s\r\n\r\n' \
   'GET /business/2026/08/12/ai-agents-lie-cheat-and-steal-that-is-putting-off-users HTTP/1.0' \
   'Host: www.economist.com' \
   |busybox ssl_client 104.18.42.19 -n economist.com \
   |sed '1s/^//' > 1.htm

   firefox ./1.htm
   #links 1.htm
   #elinks 1.htm

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

#200

Post by killix »

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.

[flagged]
Post reply on HN