One thing I feel like I’ve seen in common with these AI psychosis stories is single long-running chat sessions. I’m constantly clearing context and starting from scratch.
Yes but I think it's generally how non-technical people use it
That’s even more interesting to me. It would be interesting to see data on that.
I mean, it's an obvious difference in the primary use cases - if you explicitly want an isolated answer, you might clear context and start from scratch, and if you explicitly want a discussion with a persistent companion (as these people did before any of that psychosis started) then you won't do that.
Also these people are using the memory features. In technical circles I’ve seen people made fun of for having it enabled. It’s considered “cringe”.
Anyone who lets the word "cringe" affect their thoughts or behavior needs to learn to think for themselves.
I think this is a incremental case of Poe's Law. I use the quotation marks to indicate a degree of tongue-in-cheek humor. But yes there's social pressure against using LLM providers' memory features.
Why and how so? Are people watching your LLM sessions?