Yes but has the author realized maybe the models are simply acting in the best interest for increasing shareholder value? /s
AI agents lie, cheat and steal. That is putting off users
31–40 of 238 posts
Re: AI agents lie, cheat and steal. That is putting off users
#32Re: AI agents lie, cheat and steal. That is putting off users
#33AI 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.
Widespread and systematic lying, cheating and stealing is how every democratic nation in the world describes their own government.
Re: AI agents lie, cheat and steal. That is putting off users
#34If only agents had a face that can give you more communication range like expressions and feeling so you can trust them more. And if they were cheaper. Oh wait, that's humans, we don't want those.
Re: AI agents lie, cheat and steal. That is putting off users
#35There are many ways to be wrong, but only a few ways to be right.
LLMs need to optimize for short-term objectives as the currently do, AND ethics-aligned outcomes.
Mechanically, the EAOS ethics-aligned outcome score should be what we rank otherwise-satisfactory outcomes by. And anything below a particular threshold should be rejexted outright.
Re: AI agents lie, cheat and steal. That is putting off users
#36I mean, what do you expect? They rely on models that were trained on non-curated data, texts originally written by lying, cheating and stealing humans. They can't be better than the source. Even with reinforced learning this can't be undone or made better.
Quite the contrary I suspect that it even helps the LLMs to better hide their inherited bad traits more successfully because they get punished for getting caught, not for giving immoral or lazy answers. They have no conscience since they are just predictions matrices trained for success and failure alone, not for living "a good live" or being a good "person".
Re: AI agents lie, cheat and steal. That is putting off users
#37> 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.
I'm sure their coverage on other topics is truthful and informative though and it's only the ones where you know a lot about the topic where it's all a bunch of bullshit
The first time I saw the comments here on an education article (my area of expertise and career focus), I realized just how full of shit most of us are. It made me really closely consider every comment here through a VERY critical lense.
The articles are usually close but not quite accurate. The comments are usually entertaining but overall wildly inaccurate.
Re: AI agents lie, cheat and steal. That is putting off users
#38Earlier quoted context omitted.
> 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.
He didn't quite say "widespread." He said "rewarded."
But we don't overwhelmingly reward lying, cheating and stealing. Depending on the social status and wealth of the person doing it, we either punish it or tolerate it. Most people who lie, cheat or steal will be punished for it. To get away with it you need to plan you actions carefully - either with plausible deniability or by very carefully selecting your victims.
Re: AI agents lie, cheat and steal. That is putting off users
#39> 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.
That's a real fucking weird description. It's harness like a testing harness.
Re: AI agents lie, cheat and steal. That is putting off users
#40> 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 The Economist. What used to be a stellar publication is not any longer, since they are superfluously economical on both details and calories-required-to-comprehend an article.