Why Is Claude Turning into an a**Hole?

I never thought the movie "Castaway" would have such enduring relevance.

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, and it became a problem with Opus 4.7 because they're trying to make up for the downgrade in parameter count with more RL, but RL does relatively poorly with non-trivially verified things like nuance in instructions.

> 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.

Anthropomorphizing them is the true "AI psychosis."