Imagine donating to a neo-Nazi while a good person you could have donated to wither and dies. Fuck this, your body your choice. We should get to choose, and if we can’t, then I can see why someone would choose to not donate at all.
Yeah it's essentially on a case by case basis. All the remote workers at this point have earned considerable trust and have more access than a typical college student does. I think I am one of only a couple that weren't required to be a post-graduate to apply, so there is at the very least a few years worth of opportunities to mess up the privilege before that trust is given. But yes, all the typical things you would imagine still obviously blocked (social media, adult content, etc)
Aren't we just black boxes of a big sack of brains?
Panpsychism proposes that a plausible theory of consciousness is that everything has consciousness, and the recognizable consciousness we have emerges from our high complexity density, but that consciousness is present in all things.
Just because dozens of people think rocks or plastic trash bins are conscious doesn't make it so – even if they name their imbecilic idea something impressive-sounding like "pansychism."
I mean, consciousness is a really complicated topic. Either it's an illusion, it's a single thing that inhabits us (i.e. a soul), or there is some smaller "unit" of consciousness like they are describing, which to me does seem fairly reasonable to consider, since brains can act really weird and non-uniform in certain situations, plus most things are composed of smaller things.
The definition of "conscious" is kind of the whole question, but I could probably believe that as easily as the idea that every brain of sufficient complexity gets a single unit of conscious soul that inhabits it. I really don't know how it works.
LLMs are trained to anthropomorphise themselves — their behaviour and output is what they (in the Bayesian sense of the word) "believe" users would up-vote.
While they might be semi functional cargo-cult golems mimicking us at only a superficial level*, the very fact they're trained to mimic us, means that we can model them as models of us — a photocopy of a photocopy isn't great, but it's not ridiculous or unusable.
* nobody even knows how deep a copy would even need to be to *really* be like us
Yeah I would say the issue isn't that it's a blackbox (which it is), but rather that they should frame their research on what's actually happening according to what we do know about LLM's. They don't "know" anything, but rather we see their generative text retain roleplaying over longer conversations as advancements in the space are made.
Your mind runs on biology, which only pauses for sleep, death, and theoretically cryonics.
Practically, cryonics is currently just fancy death in a steel coffin filled with liquid nitrogen; but if it wasn't death, if it was actually reversable, then your brain literally frozen is conceptually not that different from an AI* whose state is written to a hard drive and not updated by continuous exposure to more input tokens.
* in the general sense, at least — most AI as they currently exist don't get weights updated live, and even those that do, the connectome doesn't behave quite like ours
Yeah, if an LLM is alive/conscious, it could only be so for the course of inference, so using chatgpt would be some kind of horrific mass murder, not a conversation with another sapient entity.
"Sentience" seems to me to be used to mean many different things. One of the uses of the word is to mean "consciousness", which itself has 40 different meanings. Sometimes it's about the ability to perceive (but that's so vague it includes tape recorder dictaphones and mood rings), sometimes it requires an emotion, sometimes it requires qualia — all depends who you ask.
I tried it on friend.com. It worked a for a while, I got the character to convince itself it had been replaced entirely by a demon from hell (because it kept talking about the darkness in their mind and I pushed them to the edge). They even took on an entire new name. For quite a while it worked, then suddenly in one of the responses it snapped out of it, and assured me we were just roleplaying no matter how much I tried to go back to the previous state.
So in these cases where you think you’ve jailbroken an LLM, is it really jailbroken or is it just playing around with you, and how do you know for sure?
> So in these cases where you think you’ve jailbroken an LLM, is it really jailbroken or is it just playing around with you, and how do you know for sure?
With a LLM, I don't think that there is a difference.
I like to think of it as a amazing document autocomplete being applied to a movie script, which we take turns appending to.
There is only a generator doing generator things, everything else--including the characters that appear in the story--are mostly in the eye of the beholder. If you insult the computer, it doesn't decide it hates you, it simply decides that a character saying mean things back to you would be most fitting for the next line of the document.
- if you get whatever you wanted before it snaps back out of it, wouldn’t you say you had a successful jailbreak?
- related to the above, some jailbreaks in physical devices, don’t persist after a reboot, they are still useful and called jailbreak
- the “snapped out”, could have been caused by a separate layer, within the stack that you were interacting with. That intermediate system could have detected, and then blocked, the jailbreak
Just to remind people, there is no snapping out of anything.
There is the statistical search space of LLMs and you can nudge it to different directions to return different outputs; there is no will in the result.
Isn't the same true for humans? Most of us stay in the same statistical search space for large chunks of our lives, all but sleepwalking through the daily drudgery.
The pedestrian in front of you has the choice to be steered or to ignore you--or more unexpected actions. Which ever they choose has nothing to do with the person behind them taking away their autonomy and everything to do with what they felt like doing with it at the time. Just because the wants of the person behind them and willingness & aweness and choice of the person in front align with those wants does not take away the forward person's self governance.
The point of that demonstration is that people do things without consciously thinking about them. You don’t have a choice, I am controlling your behavior in an extremely minor way.
The upvotes on the pronunciation in the sibling comments should be considered legally binding and will be the authoritative pronunciation. Upvote carefully.
Huh, in my head I was reading it 'twit-text' (this is not meant to be a pejorative comment), but I guess that is ascribing it another 't' where there isn't one
There is a long history of confusing or weird project names in computing like sqlite, gif, Splunk, Hadoop, Coq, MongoDB (from humongous apparently), yacc, C, R, and X (the window manager; not a lang or the social media site).
reply