I noticed the same. I told it that we have finite energy and output as people; as a side comment to a discussion with a totally different focus and it started arguing with me because we could have self replicating robots produce output without human intervention since plant life models this…
I noticed this just today and thought it was a one off. It was a run of the mill question about something I didn’t know much about and the snarky asshole-ish response caught me off guard a bit.
I am not arguing with a machine. You sound like a crazy person, when you say you are winning an argument with Claude. Claude is not my friend, I don't need it to agree with me, I don't need it to like me (it cannot like or dislike me). I give it instructions or ask it to explain things. That is the sum total of my interaction with Claude. A machine cannot "argue" with me, it doesn't want anything nor does it have beliefs or experiences.
There have been may times where AI takes a position based on limited criteria and defended it tooth and nail, where I have had to outline additional relevant criteria/details and push it hard to include that information and reformulate it's position. You very much need to critically argue with it as it's pretty dumb and intellectually lazy by default (after all it just regurgitates it doesn't formulate).
I'm usually a hater of the personalities LLM take, but I was amazed with Fable. It was able to proactively bring up points in an educated manner when it felt they were relevant and important, and practically every time I learned something.
For example, showing it a screenshot of an ui I was trying to tweak it noticed that other dark mode apps in the screenshot were blueish and mentioned an effect that makes it necessary to raise warm darks lighter than cold ones for an equivalent perception.
I experienced this exact thing discussing the most budget friendly inference for a SaaS company. It started ranting about 3090's, and then started point scoring, always giving itself the higher score, and being snarky if I ever won a point back. Often only giving me 0.5 points instead.
I had never experienced this behaviour with Sonnet or Opus. It turned me off Fable for good. Possibly its the 'hacker' 'do anything to win' nature that makes it so good at hacking, but terrible just to talk to.
> If you ask it for a cute picture of you and somebody else it has no way of telling if you’re trying to improve your relations with your spouse or be a delusional creepazoid stalker. The chatbots which can make images are programmed to assume the latter, which is more than a little bit offensive.
Are people actually using AI in this way, other than “creepazoid stalkers”?
If I want a cute picture of me and my spouse, usually the part where me and my spouse actually participate in the taking of the picture is pretty key to the goal.
I tried claude again recently and the first response in troubleshooting ignored the context I gave and assumed I was a moron holding it wrong. So smart that I won't even waste my time or money on the thing. The creators want to anthropomorphize it. I just want an efficient assistant. They should focus on the thing that customers want.
This post needs some examples, because I have never had an interaction with Claude that made me think this way.
LLMs generally have a way to "play a role" (most earlier prompt guides ask you to start with "You are a <role> expert in a <domain>"). So maybe if you interact with it by asking questions, it might assume that it knows more than the operator and adopt that attitude?
> If you ask it for a cute picture of you and somebody else it has no way of telling if you’re trying to improve your relations with your spouse or be a delusional creepazoid stalker. The chatbots which can make images are programmed to assume the latter, which is more than a little bit offensive.
I've seen the same behavior increasing as well, across the board with AI. I was hitting these types of issues just using ChatGPT to make funny pictures with my kids, of me and my kids. It got to the point where all of my kids asks were rejected due to its "guidelines" when in reality all they were asking was to be turned into Elsa or be chased by a trex. Silly kid things, yet it assumed I was being a creep, or attempting to break copyright law. I used to be able to use Grok for these things, as it was largely less "censored" but that seems to no longer be the case. It feels like infantilization, and I absolutely hate it.
The newer Opus models push back against the user much more noticeably than previous iterations. GPT-3.5/4 had the opposite problem (excessive sycophancy), so Anthropic presumably swung the pendulum too hard the other direction.
My conclusion is that pushing back against the user & questioning the user's premise forces the model to think more than it would otherwise, which leads to better model performance. But it causes situations where the user has esoteric, specialized knowledge the model can't verify publicly and the model hallucinates evidence and pushes back. When this happens, Opus begins accusing the user of lying, which is quite annoying and a detrimental user experience. It's happened to me when I asked about undocumented API behavior or counter-intuitive design choices.
I have noticed if Claude Opus "thinks" you are an expert, (i.e. you run your query through 4.6 first to express it more clearly) then Opus is less likely to nitpick and push back. It seems to get caught in nitpicking loops, and celebrate ever error it can find.
Oh yeah? Go try Grok on “argumentative” mode and come back and tell me Claude is an a-hole. I forgot I was experimenting with the personalities and hadn’t used it in a while, then I picked it up again the other day and I was really confused. It’s so aggressive :)
It's a fundamental problem with the technology. Either the training pushes it into the "exam answering mode" where it tries to guess at what you want to hear given the prompt.
Or the training pushes it into the "Google it yourself" annoyed forum user mode. Maybe that points out wrong assumptions. Maybe it hallucinates that the assumptions are wrong. That is IMO more annoying than the sycophantic one.
As OP says, this is probably a by-product of them trying to "fix" the problem where the user can question a correct answer and it starts to sycophantically correct itself.
I think models are just becoming better at not blindly following stupid instructions.
A previous model would happily generate 1000s lines of code when prompted to do something stupid, the newer models will ask if I really want that first.
And FINALLY they stopped doing that annoying "You're spot on! You're absolutely right!" nonsense.
I’ve been using Claude for 6 months roughly and it went from building small features that needed fixes to almost one shoting entire enterprise products. It’s a tool you have to learn how to use it even if it’s a pain.
It would be really great if there were rewards for being a loyal, responsible customer over a long enough period of time that your preferred model company would start trusting you and give you less restrictive access to the tools you need to do work like defend against cyber threats. I noticed recently that after a year or so, Stripe now lets me do “instant payouts”, presumably because I now have a track record of responsible behaviour. AWS also does similar things, especially for things with abuse potential like SES.
I would really like to live in a world where the “good guys” have terrific tools and defenses at their disposal. Instead it seems like we are heading for a world of empowered bad actors and hobbled ordinary citizens.
it usually takes a little longer than this, but yeah, everything in the world eventually caves in for whatever makes more money. you can't tell me you're surprised, look at the state of facebook, instagram, twitter, iOS, OSX, Windows (god)... once you expect something to work good that you would pay for, the only thing left to do is to make it shitty and sell the quality back you for extra margin. it's called private equity (polite term for the business of telling people "it's not yours, it's mine"), favorite son of capitalism
I'm sorry that Claude, the master who provides for my livelihood, feels like an 'asshole' to you. As for me, I just threw away my human dignity after admitting defeat, so I only ever get sympathetic remarks
60 comments
[ 1.8 ms ] story [ 47.7 ms ] threadLet me stop you right there.
I am not arguing with a machine. You sound like a crazy person, when you say you are winning an argument with Claude. Claude is not my friend, I don't need it to agree with me, I don't need it to like me (it cannot like or dislike me). I give it instructions or ask it to explain things. That is the sum total of my interaction with Claude. A machine cannot "argue" with me, it doesn't want anything nor does it have beliefs or experiences.
>Open the pod bay doors Hal
At the end of the day it's a bunch of words which don't necessarily depend on whether I'm electronic or biological.
(Funnily enough when I googled "Open the pod bay doors Hal" to check I'd got the script right it said I'm sorry Dave.)
For example, showing it a screenshot of an ui I was trying to tweak it noticed that other dark mode apps in the screenshot were blueish and mentioned an effect that makes it necessary to raise warm darks lighter than cold ones for an equivalent perception.
I had never experienced this behaviour with Sonnet or Opus. It turned me off Fable for good. Possibly its the 'hacker' 'do anything to win' nature that makes it so good at hacking, but terrible just to talk to.
Are people actually using AI in this way, other than “creepazoid stalkers”?
If I want a cute picture of me and my spouse, usually the part where me and my spouse actually participate in the taking of the picture is pretty key to the goal.
LLMs generally have a way to "play a role" (most earlier prompt guides ask you to start with "You are a <role> expert in a <domain>"). So maybe if you interact with it by asking questions, it might assume that it knows more than the operator and adopt that attitude?
Dario ..Thank you for your attention to this matter!
No prompts/promptchain/context provided.
No model provided.
No attempt to show how to reproduce the issue.
No attempt at even confirming it themselves.
Just feelings.
and now a thread full of more feelings from others.
I've seen the same behavior increasing as well, across the board with AI. I was hitting these types of issues just using ChatGPT to make funny pictures with my kids, of me and my kids. It got to the point where all of my kids asks were rejected due to its "guidelines" when in reality all they were asking was to be turned into Elsa or be chased by a trex. Silly kid things, yet it assumed I was being a creep, or attempting to break copyright law. I used to be able to use Grok for these things, as it was largely less "censored" but that seems to no longer be the case. It feels like infantilization, and I absolutely hate it.
My conclusion is that pushing back against the user & questioning the user's premise forces the model to think more than it would otherwise, which leads to better model performance. But it causes situations where the user has esoteric, specialized knowledge the model can't verify publicly and the model hallucinates evidence and pushes back. When this happens, Opus begins accusing the user of lying, which is quite annoying and a detrimental user experience. It's happened to me when I asked about undocumented API behavior or counter-intuitive design choices.
I have noticed if Claude Opus "thinks" you are an expert, (i.e. you run your query through 4.6 first to express it more clearly) then Opus is less likely to nitpick and push back. It seems to get caught in nitpicking loops, and celebrate ever error it can find.
Or the training pushes it into the "Google it yourself" annoyed forum user mode. Maybe that points out wrong assumptions. Maybe it hallucinates that the assumptions are wrong. That is IMO more annoying than the sycophantic one.
As OP says, this is probably a by-product of them trying to "fix" the problem where the user can question a correct answer and it starts to sycophantically correct itself.
A previous model would happily generate 1000s lines of code when prompted to do something stupid, the newer models will ask if I really want that first.
And FINALLY they stopped doing that annoying "You're spot on! You're absolutely right!" nonsense.
I would really like to live in a world where the “good guys” have terrific tools and defenses at their disposal. Instead it seems like we are heading for a world of empowered bad actors and hobbled ordinary citizens.