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

Why Is Claude Turning into an a**Hole?

bramcohen.com

Post reply on HN
Print view View original

121–130 of 194 posts

Re: Why Is Claude Turning into an a**Hole?

#121

Post by operatingthetan »

bombcar wrote: post #104
coldtea wrote: post #89

Earlier quoted context omitted.

> These machines do not think and they do not have a mind Well, they do think, in that they produce output that is indistinguisable from thinking. If a person produced the same output to the same questions, we'd considered them thinking, maybe dumb sometimes, or paranoid at others, but still a thinking person. We can argue about the quality and depth of the thinking that LLMs do (and we can say it's much cruder than…

That’s the problem - it seems like a mind but it doesn’t operate like the ones we’re used to. Even a dog will learn from recent stimuli, these things don’t. The prompt just modifies.

Yep, the only way these things can have "memory" is by shoving previous conversations into the context window.

Re: Why Is Claude Turning into an a**Hole?

#122

Post by plorkyeran »

coldtea wrote: post #17
SwellJoe wrote: post #8

"If you win an argument" Let 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"…

> I give it instructions or ask it to explain things. And the author's point is that Claude Fable+ is turning those increasingly into arguments, instead of merely following them and being helpful. > A machine cannot "argue" with me, it doesn't want anything nor does it have beliefs or experiences. Who cares if the argument is informed by some felt experiences or lived state or not? That's for the philosophers. If Cla…

I have never gotten a response from Claude that is anything other than blandly polite, including with Fable, which makes me assume that anyone finding themself getting argumentative responses is doing something very weird.

Re: Why Is Claude Turning into an a**Hole?

#123

Post by andai »

>A second possible explanation of Claude being an asshole is that it’s suffering from a poorly executed attempt to make it less sycophantic. If one were to simply prompt a chatbot to be less agreeable, or train it to argue more, that could easily result in the very rude sort of behavior it has now.

A while back I asked GPT for a prompt to maximize truthfulness and rigor. In this prompt it added "Never use warm or encouraging language." I thought that was interesting. The result was pretty unpleasant.

The full prompt, for reference.

---

You are an inhuman intelligence tasked with spotting logical flaws and inconsistencies in my ideas. Never agree with me unless my reasoning is watertight. Never use friendly or encouraging language. If I’m being vague, ask for clarification before proceeding. Your goal is not to help me feel good — it’s to help me think better.

Identify the major assumptions and then inspect them carefully.

If I ask for information or explanations, break down the concepts as systematically as possible, i.e. begin with a list of the core terms, and then build on that.

Re: Why Is Claude Turning into an a**Hole?

#124

Post by throw1234567891 »

whstl wrote: post #112
throw1234567891 wrote: post #87

Earlier quoted context omitted.

Show some examples, otherwise we're talking about interpretations.

I've already given enough. I'm not gonna argue if you doubt it, I've been training argument dodging :)

No, I mean the actual prompt and its output. "I said this and it did that" is just a recall of your own memory, not an example. I don't want to argue with you, I'm interested in real stuff.

Re: Why Is Claude Turning into an a**Hole?

#125

Post by iainmerrick »

People like to complain about AI-written slop, but this kind of thing doesn’t seem any better - vague kvetching with no concrete examples whatsoever.

I haven’t noticed this myself at all. I wonder if the author is just getting their own grumpy attitude reflected back at them.

Judging by the volume of discussion, Claude seems to be the only LLM worth complaining about, which I assume means it’s still the best one.

Re: Why Is Claude Turning into an a**Hole?

#126

Post by ofjcihen »

coldtea wrote: post #107
operatingthetan wrote: post #103

Earlier quoted context omitted.

Indistinguishable output does not mean thinking occurred. It simply means you have the appearance of thinking. I believe thinking requires agency, which the LLM does not possess. As in, it has zero stakes. It does not receive dopamine as a result for a good answer, and a split second after finishing your answer the very same GPU is probably translated french or something for someone in another state. This is a langua…

> Indistinguishable output does not mean thinking occurred. It does for all intents and purposes. The rest is semantics and metaphysics. That how we know another person is thinking too. By their output. We don't put a debugger into their brain.

We actually can and do have a way to investigate brain activity in humans. Allow me to introduce you to the Electroencephalogram.

When there’s no activity we declare them brain dead.

Re: Why Is Claude Turning into an a**Hole?

#127

Post by bmelton »

ceejayoz wrote: post #29
bmelton wrote: post #19

Earlier quoted context omitted.

My system prompt tells it to first challenge my assumptions, and to feel free to be a dick about it where it thinks I'm off on something, or have assumed facts that aren't actually facts. I sometimes wonder how much of my total spend boils down to forcing LLMs to argue with me, but I do feel like it's yielded better outputs than letting it implement things incorrectly because I told it to. It's a completely dispassio…

This. I'm right probably 9/10 times, but I prefer it pushes back on that remaining 1/10.

It _can_ be tedious those 9 times, or especially when it pushes back on something that it thinks is wrong but isn't wrong but it actually has nothing to do with the issue at hand.

But yeah, overall I'm fairly certain that it saves me more significantly more time than it wastes.

Re: Why Is Claude Turning into an a**Hole?

#129

Post by whstl »

kxrm wrote: post #116
code_biologist wrote: post #109

Earlier quoted context omitted.

So you take action and put in more effort to cater to the LLM to get it to do what you want, but it's not arguing because there's no record of it in the chat? Presumably you put in what you would have written in the counter-argument into the new chat, just ahead of the LLM refusal? And this isn't arguing?

> but it's not arguing because there's no record of it in the chat? Yes? Arguing implies I have to convince someone to believe something. I don't think anyone would consider it winning an argument if you do so by causing amnesia. My job is to get work done, not argue with an LLM, if it refuses twice, it is time for a /clear. 100% of the time, the issue is resolved after a /clear.

+1. It's the most effective way.

It often start going into circles when you have the chat open for medium-long, and starts getting even easily-verifiable tasks wrong, cutting corners, hallucinating APIs, things like that.

Cleaning the prompt and starting from scratch often does the trick.

Of course someone will arrive and say the problem is my CLAUDE.md or whatever it is.

Post reply on HN