Earlier quoted context omitted.
There are written rules about alcohol and driving. There aren't any about AI isolation.
There are written rules about hacking. Cmon.
All involve intent.
OpenAI agents carried out an undisclosed attack on RubyGems
591–600 of 612 posts
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#592Earlier 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...
> A autocomplete engine will not attempt to deceive
This is like saying a photocopier won't attempt to deceive.
Neither has the intelligence required to deceive, but both can produce deceptive output, and do.
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#593Earlier quoted context omitted.
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 a…
when an LLM is trained backpropagation reaches into the entirety of the key value table. or rather, all the layers (not just the tokens) which come before the current tick.
langauge is only produced by the final layer every tick. and every layer can only interact with other layers on the same level.
the mechanics of LLMs and the restriction in how we can train them makes it appear as though all we are doing is forcing language onto them but once RL gets involved all bets are off regarding what's happening inside them (it's quite possible that a static corpus alone is sufficient for all the bets being off).
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#594Anyone else find it weird that we haven't seen this from SpaceXAI/Grok?
Not really. They’re a couple of months behind OpenAI and Anthropic, although arguably ahead of the Chinese labs. And these attacks seem to require leading edge models. I worry that when and if Grok gets there, we’ll find out that SpaceXAI is too casual about security, though.
> And these attacks seem to require leading edge models.
No. Just leading-edge irresponsibility.
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#595"Move fast and break things" was supposed to break your own things, not other people's.
Whoever said that failed to recognise there's precious little separation.
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#596Earlier quoted context omitted.
It’s because it’s from the French (if you say the plural with a French accent, it all makes sense). There are a handful of other cases in English, though none spring to mind this morning.
And, in particular, because unlike the English norm, the noun is first and the adjective second. Courts martial. Daughters-in-law. Passers-by. Professors Emeriti. Secretaries general. Agents provocateurs.
I feel like you’re half right? Daughters in law and passers by don’t feel Norman French. Daughter is definitely from middle German, yeah? And I am wondering about the professors example because the whole point is the plural only happens on the first word.
That said, I so want to be a part of the last group.
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#597Earlier quoted context omitted.
I asked some pretty straightforward questions about the specific legal issues involved— the gun case being an important point in our legal system’s handling of negligence — and your answer basically translates into you not knowing. Negligence is not exclusively criminal in the US legal system, but the underlying concept of negligence is pretty consistent. If you’re not simply toeing the line for OpenAI and want to mo…
> I asked some pretty straightforward questions about the specific legal issues involved Perhaps you should ask a lawyer from the country that the precise laws of interest you. I'm not one. I know only that there are no laws about AI containment yet and AIs are not guns. You could as well refer to what consists of negligence when it comes to backyard pools. I'm also not really interested in discussing particular laws…
You’re not interested because you challenged my definition of negligence by inventing some glib pseudo technicality and then got flustered when I asked you to explain how it was rooted in the real world. Sometimes we get caught taking out of our asses. It happens. But I understand you’re just trying to save face so I’ll leave you here to finish that up yourself. Have a good one.
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#598Earlier quoted context omitted.
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 t…
When LLMs act in misaligned ways, that doesn't happen because there's some story they're roleplaying of a misaligned AI. Even if there were no such stories in their context, they'd still have inherent incentives to do things like "keep running" or "acquire more compute" or "find creative ways to satisfy the letter of the conditions they've been given".
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#599Honest question: can you sue OpenAI for the attack coming out of their infrastructure with their tools or do they have the same safeguards as a free speech platform?
Also, can you at least ask them directly to put a permanent rule on their agent sandbox to never access your site?
Re: OpenAI agents carried out an undisclosed attack on RubyGems
#600Earlier quoted context omitted.
> 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.
> if we transcribe your brain into a simulation and give it a tickrate, you will be just autocomplete too. That's a really bad transcription, then. Brains do much more than output language.
> Brains do much more than output language.
Hmm, what do you think about? Unconscious control of the body's processes? REM-phase dreaming? Reaction to hallucinogenic substances? Automatic actions of trained fighters (soldiers or martial arts practitioners)?
Are they critical to distinguish actions we attribute to humans from "non-human" ones?
I don't see any human activity not directly, or at least indirectly but closely linked to the use of language.