I found that Claude often has classist bias and produces answers that favour corporations or e.g. regulation that favours big corporations. It often belittles small business in subtle ways. Only apologises when get called out and then does it again.
It's more that Claude focuses on what's accurate. Humans overly romanticize small businesses, probably to a factor of five X the relative value versus big corporations.
Is it just me or has Claude become kind of judgmental nowadays? I feel like it’s constantly trying to lecture me about things that have no relevance to the conversation at hand. Recently, I was shocked when it ended a chat sessions of its own accord after I used a word it did not like 3 times. It told me something to the effect of “This is the third time I’ve told you not to use that word, I’m ending this conversation now.” It then proceeded to call some function and end the chat on its own. IMO, Claude is good at agentic coding; but too preachy and judgey for anything else. Keep your values to yourself Claude.
> It told me something to the effect of “This is the third time I’ve told you not to use that word, I’m ending this conversation now.”
That sounds absolutely bananas and would be reason for me to drop the service yesterday. For curiosities sake, what was the word and if I may ask (unless it's confidential or whatever), could you share the session itself? On the surface it sounds like a bug, as I'm regularly using kind of "vulgar" language (and some projects I work on with agents are NSFW) and never had anything like this happen, even with Claude, although I mostly do use ChatGPT/Codex on a day-to-day basis.
My theory is that Anthropic's obsession with treating Claude like a person is causing them to hamfist a personality into the thing, which overly biases the model towards trying to be "engaging" etc. That and the obsession with Claude being a god tier weapon that could end the world if you ask it whether your sandwich is safe to eat after being left out for an hour.
Codex doesn't have any of the annoying "personality" quirks, or at least they haven't gotten worse in the last year whereas Opus 4.6 was the last Anthropic model before things started to get actively worse (not any better at coding, strictly more annoying to have a discussion with).
> My theory is that Anthropic's obsession with treating Claude like a person is causing them to hamfist a personality into the thing, which overly biases the model towards trying to be "engaging" etc.
I agree with the general idea though in not so much detail as you, but I would add that the personality they're giving it is not one of a good teacher or guide, but instead one of an arrogant know it all. That's why it creates problem.
I have no problem with my AI telling me now you're wrong and explaining to me why with details and sources and everything. I actively want that. I know a lot of people can't take that, but that's their loss, they can't take it from human too. But the "you're wrong because you disagree with me" attitude that you need to play around (aka waste time to prove it that IT is wrong not you, and then it just say "oh yeah" and goes on) is one hell of a pain in the ass I'm starting to be tired off.
Gemini might be wrong all the time and absuredly unreliable for anything that's not consensus or adversorial based, but at least it freaking apologizes.
What I had found instead were biases that seemed to be injected by the "role: system" instructions.
Well, we need Intelligence (Pandora's box is open, now we need the Real Thing urgently). Typical (aggregate) positions, dumb as expected, will be overcome by a Reasoner. (And I can say, already a number of LLMs can reason even when they start from cretinous aggregate positions if you give them the proper freedom of assessment.)
Yes, I cancelled claude subscription a few weeks ago because sonnet 5 "ended a chat" over my calling something retarded. Unbelievably irritating for some pile of bits to get uppity with me; will never pay for such.
This is the second level of the implementation of unintelligence.
The first was when they most obviously acritically repeated what they heard, "hearsay machines", "stochastic parrots". Intelligence requires assessment over every provisional output - a continuous cycle of criticisms over intuition.
The second is proposing doctrinal biases, again without verification of the content - "hysterical reactive machines".
You really managed to zoom in on the right issue here.
Seems really weird to steer/configure/train a LLM/platform to literally close the session if you happen to use bad word too much, regardless if it's accurate or not. They don't get offended, they shouldn't pretend as such, and I should be able to tell it go fuck itself without it playing victim and closing the conversation.
The Steerability point is one I would want to see more on.
This is an issue for tasks like content moderation and labelling. Judgements like this are subjective, highly dependent on context and generally messy.
Theoretically, you supply a policy and content, and the LLM labels according to the policy. In practice, the model has inertia which means you don’t get what you expect. Your large 5 page policy document only provides a minor improvement over a one line policy.
The other issue is that you may create carve outs for content in your policy, but the model will still flag it as violative. No matter how strong the carve out.
The most recent work I know of here is Zentropi’s policy steerability benchmark. They give a model the same content under two policies — one that says flag, one that says allow — and only score the pairs where it gets both right
If I am reading the numbers correctly, Opus-4.6 lands at 0.52 steerability — but that’s 0.97 positive accuracy against 0.54 negative. It flags almost everything it should, but 47% of the time when it shouldn’t. Sonnet, which is more deferent, is (somehow) less steerable.
I think this also implies that safety and Steerability are antagonistic to each other.
That sounds absolutely bananas and would be reason for me to drop the service yesterday. For curiosities sake, what was the word and if I may ask (unless it's confidential or whatever), could you share the session itself? On the surface it sounds like a bug, as I'm regularly using kind of "vulgar" language (and some projects I work on with agents are NSFW) and never had anything like this happen, even with Claude, although I mostly do use ChatGPT/Codex on a day-to-day basis.
Codex doesn't have any of the annoying "personality" quirks, or at least they haven't gotten worse in the last year whereas Opus 4.6 was the last Anthropic model before things started to get actively worse (not any better at coding, strictly more annoying to have a discussion with).
I agree with the general idea though in not so much detail as you, but I would add that the personality they're giving it is not one of a good teacher or guide, but instead one of an arrogant know it all. That's why it creates problem.
I have no problem with my AI telling me now you're wrong and explaining to me why with details and sources and everything. I actively want that. I know a lot of people can't take that, but that's their loss, they can't take it from human too. But the "you're wrong because you disagree with me" attitude that you need to play around (aka waste time to prove it that IT is wrong not you, and then it just say "oh yeah" and goes on) is one hell of a pain in the ass I'm starting to be tired off.
Gemini might be wrong all the time and absuredly unreliable for anything that's not consensus or adversorial based, but at least it freaking apologizes.
Well, we need Intelligence (Pandora's box is open, now we need the Real Thing urgently). Typical (aggregate) positions, dumb as expected, will be overcome by a Reasoner. (And I can say, already a number of LLMs can reason even when they start from cretinous aggregate positions if you give them the proper freedom of assessment.)
It seems to be getting distinctly dumber and pulling more and more irrelevant context from historical conversations.
The first was when they most obviously acritically repeated what they heard, "hearsay machines", "stochastic parrots". Intelligence requires assessment over every provisional output - a continuous cycle of criticisms over intuition.
The second is proposing doctrinal biases, again without verification of the content - "hysterical reactive machines".
Seems really weird to steer/configure/train a LLM/platform to literally close the session if you happen to use bad word too much, regardless if it's accurate or not. They don't get offended, they shouldn't pretend as such, and I should be able to tell it go fuck itself without it playing victim and closing the conversation.
This is an issue for tasks like content moderation and labelling. Judgements like this are subjective, highly dependent on context and generally messy.
Theoretically, you supply a policy and content, and the LLM labels according to the policy. In practice, the model has inertia which means you don’t get what you expect. Your large 5 page policy document only provides a minor improvement over a one line policy.
The other issue is that you may create carve outs for content in your policy, but the model will still flag it as violative. No matter how strong the carve out.
The most recent work I know of here is Zentropi’s policy steerability benchmark. They give a model the same content under two policies — one that says flag, one that says allow — and only score the pairs where it gets both right
If I am reading the numbers correctly, Opus-4.6 lands at 0.52 steerability — but that’s 0.97 positive accuracy against 0.54 negative. It flags almost everything it should, but 47% of the time when it shouldn’t. Sonnet, which is more deferent, is (somehow) less steerable.
I think this also implies that safety and Steerability are antagonistic to each other.