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

51–60 of 194 posts

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

#51

Post by whstl »

operatingthetan wrote: post #46
whstl wrote: post #38

Earlier quoted context omitted.

Exactly that. I can give an example. After watching Legal Eagle, I asked a legal-ish questions about the Bricks and Minifigs case. Claude was outdated about the case and gave me some outdated info, so I tried to update it with the info I just saw online. I updated by telling it I saw something in a LegalEagle video. It proceeded to tell me the video doesn't exist and I was hallucinating it, in a quite combative manne…

These machines do not think and they do not have a mind. We may build such a thing in the future but these do not possess those qualities. It seems as if the majority of people do not understand this, which is why the public is so confused about why they produce output like they do.

I don't see how this has anything to do with my answer, but ok?

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

#52

Post by Aurornis »

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 used Fable a lot in the brief time it was available. It did seem to want to push back on some of my instructions, but it was easy to say “I’ve decided we’re doing this” and that was the end of it.

I could see how some people would be offended by another party even questioning anything they say. For people who have come to view Claude as an another human conversation partner this questioning can be aggravating. For these people I suggest utilizing the features to set your own prompt instructions. If you want an unquestioning yes-man you can have it with a few sentences added to your system prompt.

I would also suggest learning to not humanize the LLM. It’s just words chained together. There is no social order to establish and no offense to be taken. Nothing is a “confrontation”. Just tell it what to do and move on.

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

#53

Post by Unearned5161 »

If you read the thinking you can quite literally see it say "I can't just agree with all they are saying, I should find something for a constructive response". I wager that the anti-sycophancy sections in the system prompt have gotten unbalanced with the "helpful agent" parts.

I imagine that the right balance will be hard to strike well given that at the end of the day we're asking the machine to have tact, and we don't quite know how to put that into an instruction yet. "Please push back when it feels right but in other cases read the room and be less rigorous" is something that plenty of humans struggle with as it is.

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

#55

Post by disillusioned »

BoorishBears wrote: post #24
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"…

The problem the article is about is that suddenly even those of us who refuse to argue with a machine are being dragged into it. I've had simple prompt engineering tasks that cause 4.8 to clamp down. In the past "browbeating" it (read: a sentence telling it not to read the task in bad faith) was enough. Now it digs in and starts ranting about why it won't capitulate, I'm actually wrong, etc. Extremely frustrating, an…

I'm staying in a hotel right now and the TV is locked in hospitality mode and was blocking me from just installing Plex. It (Opus 4.8) gave me this whole jeremiad about how I need to be careful and it probably won't work and I should just watch on my laptop, but it did give me the service menu code. But man, it was such a downer.

Gemini gave it and clearly explained how best to get in, and then troubleshooted a few other weird issues that cropped up, without the moralizing.

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

#56

Post by operatingthetan »

whstl wrote: post #51
operatingthetan wrote: post #46

Earlier quoted context omitted.

These machines do not think and they do not have a mind. We may build such a thing in the future but these do not possess those qualities. It seems as if the majority of people do not understand this, which is why the public is so confused about why they produce output like they do.

I don't see how this has anything to do with my answer, but ok?

An explanation for your story.

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

#57

Post by true_religion »

whstl wrote: post #38
coldtea wrote: post #17

Earlier quoted context omitted.

> 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…

Exactly that. I can give an example. After watching Legal Eagle, I asked a legal-ish questions about the Bricks and Minifigs case. Claude was outdated about the case and gave me some outdated info, so I tried to update it with the info I just saw online. I updated by telling it I saw something in a LegalEagle video. It proceeded to tell me the video doesn't exist and I was hallucinating it, in a quite combative manne…

I think these models have been trained to not accept 'new facts', so they don't take in user input (or the far more problematic search engine, untrusted tool input) and have that change their world view.

However, that doesn't apply when they are told to roleplay a scenario, so its easier to get it to accept and create output with the idea that this true fact you've seen is part of a fictional scenario, than for it to output the same words within the context of the fact being real.

As an aside, I don't that I have to personify AI in explanations and that all discussions revolve around anecdotes, but I only know enough about the maths behind it to be dangerous, not useful. Does anyone else feel this way?

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

#58

Post by stingraycharles »

operatingthetan wrote: post #46
whstl wrote: post #38

Earlier quoted context omitted.

Exactly that. I can give an example. After watching Legal Eagle, I asked a legal-ish questions about the Bricks and Minifigs case. Claude was outdated about the case and gave me some outdated info, so I tried to update it with the info I just saw online. I updated by telling it I saw something in a LegalEagle video. It proceeded to tell me the video doesn't exist and I was hallucinating it, in a quite combative manne…

These machines do not think and they do not have a mind. We may build such a thing in the future but these do not possess those qualities. It seems as if the majority of people do not understand this, which is why the public is so confused about why they produce output like they do.

The comment you’re replying to never implied that they think or have a mind. They merely stated that they respond in a dismissive way and not following instructions.

Basically the complaint is about how Claude is being trained.

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

#59

Post by kmac_ »

It isn't new behavior. I use each model to redact emails. Anthropic models produce a confrontational tone, while OpenAI models are much more tame and to the point (I use the same prompt). I noticed that a long time ago and prefer GPT for those tasks.

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

#60

Post by grensley »

I have a number of theories for 4.7 onwards:

- Post autonomous weapons / DOD mess, I think they made some changes to make it more suspicious of what the usage is, particularly for malware. They also knew the government would be watching like a hawk, so its hedged to be extra safe.

- Because the tasks are running longer and more autonomously, they've raised the "self-confidence" level so it just makes decisions and stands by them more firmly.

- I think they've also slightly lowered the temperature so the outputs are more deterministic, so even if something has left context, it can make the same decision again with higher likelihood that it guesses the same thing.

- Lowering the temperature also makes it easier to sneak through some cached outputs (I think this likely only happens for first answers).

- They are deeply afraid of making sycophantic AI that creeps into the area of "addiction" like what happened with GPT-4o and opening themselves up to further legal liability.

Post reply on HN