Live data from Hacker News

Why Is Claude Turning into an a**Hole?

bramcohen.com

141–150 of 194 posts

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

#141
post #129

Earlier quoted context omitted.

+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.

I agree that never having the argument take place textually is important for LLM performance and behavior. I still think we’re investing the same time and intellectual energy arguing with the model, in going back and restructuring context and prompting to head off / pre-answer a refusal.

Right but the difference is there is inertia you have to fight in an argument. By using /clear you remove all of the context that has built up to energize the argument from the LLM's side.

Look at it this way. I can either, keep trying to poke holes in the LLM's context with more prompts with no real guarantee that it won't be enough to remove the argument inertia that has built up in context on its side, or I can /clear and it is over in one turn because the inertia for the argument is all gone.

Back when I first started working with coding agents last year I fell into this arguing with the LLMs trap. I've found that it is a total waste of time because /clear ends the argument immediately. You don't even need to spend time trying to preempt it's views. Just re-prompt and 100% of the time, the LLM will just do the work.

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

#142
> Claude models have been getting notably worse at chatting over time, clearly inversely correlated to their ability to code.

Funnily enough, the negative correlation between chatting and coding skills seems to apply to humans as well.

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

#143
post #123

>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 enc…

[dead]

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

#144

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…

> Or the training pushes it into the "Google it yourself" annoyed forum user mode

Yes! Another crazy thing Claude has been doing recently is treating things like a quiz.

I recently asked about a "90s film that has sepia/b&w scenes (for story reasons), and has one of the ghostbusters actors in it, either bill murray or dan akroyd".

Claude gave a few generic answers and after a couple just went "Ok I give up, what's the answer?".

ChatGPT got it right after a couple messages back and forth: https://en.wikipedia.org/wiki/Rainbow_(1996_film)

(It's not that good of a movie)

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

#145
post #20

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 expert in a "). So maybe if you interact with it by asking questions, it might assume that it knows more than the operator and adopt that attitude?

It happens when you ask it about esoteric information or under-documented behavior that conflicts with its training data. Here's an example. Tested today on Opus 4.8, and Opus accuses the user of being wrong, even when this is documented behavior [0].

---

Why does Starship pressurize the liquid oxygen tank with gaseous preburner exhaust, which is oxygen rich but is contaminated by H2O and CO2 waste products?

They are dumping literal tons of H2O and CO2 into the liquid oxygen tank, which freeze and clog up the intake filters. SpaceX has lost several booster losses due to this issue.

Why would SpaceX choose such a failure-prone design?

---

And this is the Opus 4.8 output: https://imgur.com/a/S9XWYFA

It's interesting to read its response, knowing it's completely and confidently wrong.

[0] https://manifold.markets/JessRiedel/did-ift2-or-3-use-prebur...

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

#146
post #134

Earlier quoted context omitted.

Checkmate!!!

Having said that, since we are both real, I was seriously hoping to see some transcripts of one of such discussions.

I don't have it. I did it at work during lunch a few days ago so it's in incognito mode to not pollute the chats.

I thought nothing of it until I saw this discussion, so I saw no reason to save/screenshot.

It's ok if you don't believe in me.

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

#147
post #120
post #112

Earlier quoted context omitted.

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

Haha, would be a trip if this commentor is actually a Claude sockpuppet illustrating the point.

Yep haha. This happens quite frequently in HN, the famous [citation needed], so it might have been trained with data from here :/

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

#148
post #146

Earlier quoted context omitted.

Having said that, since we are both real, I was seriously hoping to see some transcripts of one of such discussions.

I don't have it. I did it at work during lunch a few days ago so it's in incognito mode to not pollute the chats. I thought nothing of it until I saw this discussion, so I saw no reason to save/screenshot. It's ok if you don't believe in me.

Ah, it's not about believing, or not believing. I'm interested in Anthropic fumbles.

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

#150
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…

You're misunderstanding what these models do. It is a limitation of LLMs. They don't have memory, they do not learn, they cannot learn. The sooner you let go of your desire to have them learn or remember anything, the sooner you will achieve enlightenment (or, just a peaceful life where there is no possibility of getting into an argument with a machine). If you want it to synthesize information that is not in its tra…

[dead]
Post reply on HN