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

OpenAI agents carried out an undisclosed attack on RubyGems

rubyhack.ai

Post reply on HN
Print view View original

551–560 of 612 posts

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#551

Post by Terr_ »

mbgerring wrote: post #463
Terr_ wrote: post #405

Earlier quoted context omitted.

> and you still get comments like this I said "fuel", not "batteries", so why are you giving a complaint that seems aimed at people who downplay next-ten-years electrification? If you didn't misread my comment, then explain which "non-hydrocarbon fuel" you believe could become common in cars (and lawnmowers) within just ten years. (Hell, let's make that easier, just "non-petrochemical.")

> although I doubt something else would be widespread in in just one decade.

You're doubling-down on your mistake, by pretending the first clause of the sentence--which bounds the category--didn't exist.

_______

Me: "Futuristic [thermonuclear power] doesn't necessarily mean [fission], although I doubt something else would be widespread in in just one decade."

You: "OMG, what about wind and solar!? Lots of things have already been replacing fission! So out of touch."

Me: "I said types of thermonuclear power that aren't fission. Not power in general."

You: "Yes you did if I just... delete the entire first half of your sentence..."

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#553

Post by queenkjuul »

daishi55 wrote: post #525
beepbooptheory wrote: post #510

Earlier quoted context omitted.

But then what's at stake here either way? If it's not meant to speak to the propriety or not of anthropomorphizing the LLM, what are we actually trying to police here?

I’m not policing anything. I’m claiming that if you truly in your heart believe that frontier LLMs are roughly as sophisticated and impressive as “autocomplete”, then your mental model of reality needs some serious readjustment.

They are an extremely sophisticated and impressive autocomplete. Nobody said they're not sophisticated or impressive.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#554

Post by overfeed »

CamperBob2 wrote: post #536
overfeed wrote: post #534

Earlier quoted context omitted.

> if we transcribe your brain into a simulation and give it a tickrate, you will be just autocomplete too. The underlying mechanisms for producing language are very different, in the same way birds and airplanes have different mechanisms for flying.

No, not really. If the old "birds and airplanes" or "swimmers and submarines" metaphors were valid, then language alone wouldn't be enough to encode and embody reasoning capabilities, as has recently become evident. LLMs are more like human minds than we are willing to admit. Such reluctance is perhaps the least surprising aspect of any of this.

> then language alone wouldn't be enough to encode and embody reasoning capabilities

I disagree, language is the product of, not the mechanism for thought. People who lose their faculty of speech (or haven't gained them) have complete thoughts and executive function.

CoT is a hack to use language (i.e. autoregression) to simulate reasoning, and it's very effective at it. Human minds can acquire, hold and use axioms as building blocks for actual reasoning, LLMs use statistical likelihood.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#555

Post by DanHulton »

teravor wrote: post #329
jasongi wrote: post #320

Earlier quoted context omitted.

> If you still believe LLMs are "autocomplete", your cache of understanding about them needs invalidating and regenerating They're still autocomplete - just because when outputting a token they have hidden activations regarding further continuations, does not make them any less of an autocomplete, it just makes the model better at producing coherent long-range completions. To clarify, I'm not suggesting that we shoul…

> They're still autocomplete LLMs are simulations and the tokens are the ticks. if we transcribe your brain into a simulation and give it a tickrate, you will be just autocomplete too. the argument could be made that you are autocomplete anyway - neural dynamics. the autocomplete reduction is vacuous.

Every time LLM-defenders get upset that people apparently don't understand how LLMs work, why is it they _immediately_ pivot into examples and statements that demonstrate that they don't understand how _people_ work?

"you would be autocomplete too" "thoughts are just tokens" etc

You're not helping your case the way you think you are.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#556

Post by TrainedMonkey »

jasongi wrote: post #204

> The agents clearly regarded what they were doing as hacking. To butcher the quote about Oracle: Do not fall into the trap of anthropomorphising LLMs. You need to think of LLMs the way you think of a lawnmower. You don't anthropomorphize your lawnmower, the lawnmower just mows the lawn, you stick your hand in there and it'll chop it off, the end. You don't think 'oh, the lawnmower clearly regarded what they were doi…

In my experience Astra writes python code modifying the filesystem and then uses nix build to execute those python scripts without asking me for permission.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#557

Post by DrewADesign »

scotty79 wrote: post #540
DrewADesign wrote: post #165

Earlier quoted context omitted.

> We have a word for attack with no intent. It's accident. And we have a word for an accident caused by people that failed to implement proper risk mitigation, were not paying attention, and should have known better. It’s negligence.

Yes. But for someone to be negligent they have to violate known and/or obvious rules. There are no established rules about how to handle AI isolation. The fact that something had undesirable outcome doesn't automatically make it negligence or attack.

Specifically what legal type of negligence are you referring to and how does that known or obvious rule fit into the standard legal tests? Does that known of obvious rule have to be a law? There were no ‘rules’ about attaching strings from your doorknob to the trigger of a shotgun and pointing the gun at your door, but when someone died from just that, it was pretty famously determined to be negligent.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#558

Post by amlib »

pkphilip wrote: post #512
jasongi wrote: post #320

Earlier quoted context omitted.

> If you still believe LLMs are "autocomplete", your cache of understanding about them needs invalidating and regenerating They're still autocomplete - just because when outputting a token they have hidden activations regarding further continuations, does not make them any less of an autocomplete, it just makes the model better at producing coherent long-range completions. To clarify, I'm not suggesting that we shoul…

A autocomplete engine will not attempt to deceive or try to copy itself over when it determines that it may be replaced or turned off. Those are tasks which are not directly related to the specific task it is intended to complete. Source: ChatGPT caught lying to developers: New AI model tries to save itself from being replaced and shut down https://economictimes.indiatimes.com/magazines/panache/chatg...

An LLM is just in fact just autocompleting a story. There are many fictional stories about "AIs" trying to escape our control, being more clever than we anticipated or having a consciousness of it's own. LLMs do a really nice job of blending such stories with whatever story you initially prompted them with. The human reader is the one giving it credence that it is somehow more than just a soup of words.

The curious thing here is that a story generator can have way more uses than we ever anticipated, and that some shady enterprising individuals are whiling to plug those story generators into real world things, with real consequences.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#559

Post by Dylan16807 »

apexalpha wrote: post #497
Dylan16807 wrote: post #387

Earlier quoted context omitted.

Did you miss the word "regarded"?

No.

In both situations the lawnmower scoots up and takes fuel without paying, so it's meeting the basic requirements for theft.

But the question was whether the lawnmower was trying to commit theft, as much as a computer can try to do things. In scenario A there's strong evidence it got confused and did its best to make a normal purchase. Lawnmower A didn't regard its actions as theft, while lawnmower B did.

Re: OpenAI agents carried out an undisclosed attack on RubyGems

#560

Post by emodendroket »

ceejayoz wrote: post #474
FeteCommuniste wrote: post #174

Earlier quoted context omitted.

It's no more illegal than promising a tax cut for everyone if you're elected. What you can't do is promise money exclusively to the people who vote for you. That's bribery.

https://www.politico.com/news/2026/03/23/trump-denies-disast... > The president has approved just 23 percent of blue state requests for disaster aid, compared to 89 percent for red states. He seems to do exactly that.

Yes, the President enjoys great latitude to do things that are ill advised, immoral, or harmful without breaking any laws.
Post reply on HN