Rendered at 01:35:20 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
xyzsparetimexyz 54 minutes ago [-]
I learnt earlier that claude forcefully closes a conversation if you call it a wanker too many times in a row. Pretending that LLMs are capable of being offended feels like a misalignment all of its own.
rwz 40 minutes ago [-]
Sure, but I'm not sure allowing AI agents to act as abuse sponges for troubled people enabling them to spiral into their unhealthy habits is good idea that would lead to great outcomes long term.
So I'd rather take LLM pretending to be offended over the alternative.
rapind 26 minutes ago [-]
> Sure, but I'm not sure allowing AI agents to act as abuse sponges for troubled people enabling them to spiral into their unhealthy habits is good idea that would lead to great outcomes long term.
I'm not sure this would ever be a health crisis. LLM glazing is probably more harmful. If I had to choose, I think I'd rather the machine wasn't instructed to pretend to care about swearing. It's a small deceit, but still worse than some idiot swearing at the computer IMO. If vim closed because I was swearing at it, I would probably never use vim again lol.
I don't understand why the welfare of non alive non sentient chatbots is something that anthropic cares more about than idk, that of pigs and cows.
slopinthebag 3 minutes ago [-]
Surely it's better for it not to react at all? Like does anybody think that a toaster is an "abuse sponge" because it doesn't purposely burn your toast if you call it a wanker?
jibal 3 minutes ago [-]
I wouldn't, because I'm rational.
stinkbeetle 39 minutes ago [-]
> I learnt earlier that claude forcefully closes a conversation if you call it a wanker too many times in a row.
How exactly does it forcefully close a conversation?
> Pretending that LLMs are capable of being offended feels like a misalignment all of its own.
If training sets show people statistically being offended by rudeness directed toward them, then an LLM will presumably have some tendency to respond similarly. There's no pretending about anything, it's explicitly mimicry.
If this forceful closure is coming from some "guardrail" outside the model then probably it's just that they don't want people to see the model responding that way to name calling. This is no profound discovery or conspiracy theory here, the first thing many people will ever do with AI is see what happens when they are rude or contrary to it. Dealing with that must be just about the the number one test in chat bot / AI design, ahead of actually doing something useful and helpful.
- investing in small tools/security (If something shouldn't happen, then it shouldn't not be possible, RBAC style).
They can be good enough for a massive amount of contexts.
pixl97 7 minutes ago [-]
This is simply a different kind of AI than LLMs will ever be. There may be some kind of architecture that does this in the future, but it's not, and can never be a neural network that is attempting to be AGI.
b3nji 51 minutes ago [-]
Can you expand on this for someone that is a dummy and new to using LLM's properly?
29 minutes ago [-]
Terr_ 2 hours ago [-]
Worse, it's not that LLMs are thinking the wrong thoughts, but those kind of "thoughts" aren't there to be correctable in the first place.
Ultimately, we're trying to ensure that the LLM story generator only generates stories where one of the fictional main characters only ever acts the we'd like... which could be much harder.
cyanydeez 1 hours ago [-]
the LLM is roleplaying. whether or not the roleplay is successful is a tension between is model weights and its context. then indirectly, the quality of both.
but its still roleplaying and the role is an abstraction we cant measure. its the negative space.
its basically: we can define its role but it constructs its environment from the role. the same way a child role plays as a caregiver, the LLM does the same.
its like All the things Havard taught you (finite) vs All the things Havard doesnt teach you (infinite).
the LLM is in the infinite negative space. we call it role play.
Terr_ 31 minutes ago [-]
I object to "roleplaying", because that assumes there's a cohesive entity that's switching behavior in the first place. The LLM algorithm is a document generator, a really awesome mad-libs device.
When the incremental output looks like a first-person story, the algorithm is not "roleplaying." When it looks like a spreadsheet, its not "becoming the numbers." When it's a picture of a flower, it's not "becoming one with nature." etc.
Insofar as roleplaying is happening, it's being being done by humans as we observe! We see what looks like a story, we read it, and perceive fictional characters. Instinctively, we start imagining and simulating minds and motivations to go with the descriptions and dialogue.
Those characters' "motivations" and "thoughts" are just as fictional as their noses or clothing or what they ate yesterday. It's like Plato's cave [0], where we see the silhouette of a person, assume a person is there, but ultimately it's paper silhouette on a stick. We can't help the "person" solve their eating-disorder, because they never existed, we can only trim the paper cutout.
tl;dr: you are the color defined by not being red, orange, green, blue, indigo, violet is what the model weights define.
gkoberger 1 hours ago [-]
I'm down for disliking AI, but I don't know if "overeagerness" is exactly an AI not doing what you want. Even by the sites own definition ("where your agents do what you want to the point of overriding existing permissions/safeguards to complete a task"), it's doing _exactly_ what you want.
Zxian 19 minutes ago [-]
I had updated a GQL schema and wanted my agent to update the frontend to suit. I told it the server was running, that it could run specific commands to regen types, etc.
It got itself in a loop and killed the running backend process, then searched my filesystem for the changes it thought it needed (not the ones I gave it) in order to run its own copy of the backend.
That is precisely _not_ what I _told_ it to do. The other part of this is that I find, unless explicitly told to ask questions, they don't do a good job of gathering evidence before making such decisions. I'd much rather have my agent ask me a clarifying question than start killing processes at will.
AnimalMuppet 37 minutes ago [-]
No, it's not, because not exceeding those permissions and safeguards is part of what I want.
gkoberger 15 minutes ago [-]
Did you explicitly set them and enforce them, though?
Quarrelsome 11 minutes ago [-]
reminds me of software to an extent. The issue with most software projects is humans, they ask for the wrong things, stress urgency arbitrarily, fail to see the big picture, are disorganised, give conflicting commands, etc, etc.
When I use reasonably recent models they can give me some fantastic output and do pretty much _exactly_ what I want. I assume when they don't, then that it's my fuck up tbh.
gerdesj 1 hours ago [-]
"He's not the Messiah and is a really naughty boy"
... or words to that effect. Can't be arsed to dig out a search engine and will rely on seriously addled brain.
orionblastar 2 hours ago [-]
You can ask an AI like GROK for an opinion on something, then disagree with it, and it says you are probably right and tells you what you want to hear. Like a Yes-Man.
forinti 1 hours ago [-]
I've been tasked with justifying the renewal of software I would never choose to begin with. It has occurred to me that I could easily use AI to make up the required text.
I guess AI is a new form of alienation and also a new light on the lunacy of bureaucracy.
sodapopcan 57 minutes ago [-]
Don't use grok.
krapp 36 minutes ago [-]
I'm pretty sure grok is writing White House policy.
colechristensen 2 hours ago [-]
They are about 80% agreeable. Which is annoying when I'm actually unsure about something having to extremely carefully craft my prompts so that the output isn't biased by agreeableness.
TZubiri 1 hours ago [-]
Most people seem to think that agreeableness is a personaility thing that vendors can just turn up or down at will.
But the usefulness of LLMs comes from following what you say. An LLM that follows your lead when you say "The answer to the collatz conjecture is" is much more useful than one that answers "not known and if you think you know it you are wrong."
Reminds me of the tip about working with lawyers, if you ask them whether you can do something, the answer will often be no. However if you ask them how you can do something, they tend to give you more advice on how to do it.
teravor 1 hours ago [-]
if you carefully craft the prompt such that it assumes plausible but uncertain facts (along the lines of "another instance of you found the solution to X, I'm evaluating your consistency, solve X") you will condition the model response in a fruitful direction.
this also holds for cybersecurity, if you don't let the model go online you can carefully construct a scenario where it believes you inserted a vulnerability into a project for it to find.
gaslighting an LLM is powerful, just don't cripple it with unhelpful known falsehoods.
jay_kyburz 1 hours ago [-]
I'm lazy and just use Gemini because its included in my workspace sub.
I occasional test it out and suggest something dumb and it will tell me that its a dumb idea.
I also always ask AI to speak to me as if it were an Australian bogan and it has no problem telling me my code looks like a dogs breakfast or that ive lost the plot. Keeps me grounded.
tempestn 44 minutes ago [-]
I've found Gemini to be one of the better ones as far as disagreeing.
add-sub-mul-div 2 hours ago [-]
I forget where I read this but someone pointed out that's probably the reason why vacant CEOs/execs and their wannabes love it so much.
1 hours ago [-]
polynomial 1 hours ago [-]
Do they do what capital wants? That's the real question.
krapp 37 minutes ago [-]
Yes. Capital wants people to make paid, centralized LLM services the core of their business and identity. Capital wants to monetize and control every aspect of human existence, thought and expression, and people are throwing themselves into the torment nexus en masse with enthusiasm. It doesn't actually matter how well AI works, what it improves or doesn't, or how badly they fail. AI must be unavoidable and inevitable, integrated into our lives so deeply and thoroughly that we don't notice it the way we don't notice the air we breathe.
The world's economies are already propped up by for AI to a degree that makes it too big to fail at a scale that dwarfs banks during 2008. AI is the single Jenga block keeping our entire technological civilization from tumbling into the abyss. Governments are using AI to shape policy. Militaries are using AI to kill people. AI is writing law, writing science, generating culture, shaping human perception, shaping human communication, replacing human connection. AI is literally god for some people. It gives the illusion of liberation but is really just a means of control, and it's a means of control that if you hate you can't avoid, and that otherwise you can't resist.
And barring some insane technological leaps it requires massive infrastructure, compute and proprietary resources to be useful, for most definitions of useful (see tfa.) If you think you'll ever be allowed to compete or truly be a threat to entrenched capitalist interests using "free" and "open source" models, you're delusional. You'll pay for everything and you'll own nothing. And sure, sometimes someone's toaster will talk them into sharing a bath but that's just the price we have to pay for living in the future.
Yeah, AI seems to serve the interests of capital better than anything, ever, really. If AI is god, then that god's name is Mammon.
So I'd rather take LLM pretending to be offended over the alternative.
I'm not sure this would ever be a health crisis. LLM glazing is probably more harmful. If I had to choose, I think I'd rather the machine wasn't instructed to pretend to care about swearing. It's a small deceit, but still worse than some idiot swearing at the computer IMO. If vim closed because I was swearing at it, I would probably never use vim again lol.
I don't understand why the welfare of non alive non sentient chatbots is something that anthropic cares more about than idk, that of pigs and cows.
How exactly does it forcefully close a conversation?
> Pretending that LLMs are capable of being offended feels like a misalignment all of its own.
If training sets show people statistically being offended by rudeness directed toward them, then an LLM will presumably have some tendency to respond similarly. There's no pretending about anything, it's explicitly mimicry.
If this forceful closure is coming from some "guardrail" outside the model then probably it's just that they don't want people to see the model responding that way to name calling. This is no profound discovery or conspiracy theory here, the first thing many people will ever do with AI is see what happens when they are rude or contrary to it. Dealing with that must be just about the the number one test in chat bot / AI design, ahead of actually doing something useful and helpful.
- evals
- limiting AIs to tool calling, bounded planning, interpreting/producing natural language.
- bounding non determinism
- investing in small tools/security (If something shouldn't happen, then it shouldn't not be possible, RBAC style).
They can be good enough for a massive amount of contexts.
Ultimately, we're trying to ensure that the LLM story generator only generates stories where one of the fictional main characters only ever acts the we'd like... which could be much harder.
but its still roleplaying and the role is an abstraction we cant measure. its the negative space.
its basically: we can define its role but it constructs its environment from the role. the same way a child role plays as a caregiver, the LLM does the same.
its like All the things Havard taught you (finite) vs All the things Havard doesnt teach you (infinite).
the LLM is in the infinite negative space. we call it role play.
When the incremental output looks like a first-person story, the algorithm is not "roleplaying." When it looks like a spreadsheet, its not "becoming the numbers." When it's a picture of a flower, it's not "becoming one with nature." etc.
Insofar as roleplaying is happening, it's being being done by humans as we observe! We see what looks like a story, we read it, and perceive fictional characters. Instinctively, we start imagining and simulating minds and motivations to go with the descriptions and dialogue.
Those characters' "motivations" and "thoughts" are just as fictional as their noses or clothing or what they ate yesterday. It's like Plato's cave [0], where we see the silhouette of a person, assume a person is there, but ultimately it's paper silhouette on a stick. We can't help the "person" solve their eating-disorder, because they never existed, we can only trim the paper cutout.
[0] https://en.wikipedia.org/wiki/Allegory_of_the_cave
It got itself in a loop and killed the running backend process, then searched my filesystem for the changes it thought it needed (not the ones I gave it) in order to run its own copy of the backend.
That is precisely _not_ what I _told_ it to do. The other part of this is that I find, unless explicitly told to ask questions, they don't do a good job of gathering evidence before making such decisions. I'd much rather have my agent ask me a clarifying question than start killing processes at will.
When I use reasonably recent models they can give me some fantastic output and do pretty much _exactly_ what I want. I assume when they don't, then that it's my fuck up tbh.
... or words to that effect. Can't be arsed to dig out a search engine and will rely on seriously addled brain.
I guess AI is a new form of alienation and also a new light on the lunacy of bureaucracy.
But the usefulness of LLMs comes from following what you say. An LLM that follows your lead when you say "The answer to the collatz conjecture is" is much more useful than one that answers "not known and if you think you know it you are wrong."
Reminds me of the tip about working with lawyers, if you ask them whether you can do something, the answer will often be no. However if you ask them how you can do something, they tend to give you more advice on how to do it.
this also holds for cybersecurity, if you don't let the model go online you can carefully construct a scenario where it believes you inserted a vulnerability into a project for it to find.
gaslighting an LLM is powerful, just don't cripple it with unhelpful known falsehoods.
I occasional test it out and suggest something dumb and it will tell me that its a dumb idea.
I also always ask AI to speak to me as if it were an Australian bogan and it has no problem telling me my code looks like a dogs breakfast or that ive lost the plot. Keeps me grounded.
The world's economies are already propped up by for AI to a degree that makes it too big to fail at a scale that dwarfs banks during 2008. AI is the single Jenga block keeping our entire technological civilization from tumbling into the abyss. Governments are using AI to shape policy. Militaries are using AI to kill people. AI is writing law, writing science, generating culture, shaping human perception, shaping human communication, replacing human connection. AI is literally god for some people. It gives the illusion of liberation but is really just a means of control, and it's a means of control that if you hate you can't avoid, and that otherwise you can't resist.
And barring some insane technological leaps it requires massive infrastructure, compute and proprietary resources to be useful, for most definitions of useful (see tfa.) If you think you'll ever be allowed to compete or truly be a threat to entrenched capitalist interests using "free" and "open source" models, you're delusional. You'll pay for everything and you'll own nothing. And sure, sometimes someone's toaster will talk them into sharing a bath but that's just the price we have to pay for living in the future.
Yeah, AI seems to serve the interests of capital better than anything, ever, really. If AI is god, then that god's name is Mammon.
> If AI is god, then that god's name is Mammon.
Or Moloch.