There is this BBC’s report released in May 2026. However, there are also Tim Hua’s experiment and the Spiral Bench (alas, neither of them is run on models after GPT-5.2) which imply that newer Western models are less sycophantic.
Additionally, I have heard that math journals regularly receive slop from users convinced by the AIs to the point that even other AIs can see through it. Rhe criticism was ~one prompt away!
Thanks! The two cases profiled seem to both be from last year (August of what’s presumably 2025 for Adam, April 2025 for Taka). But it does mention that
In the test, the latest version of ChatGPT, model 5.2, and Claude were more likely to lead the user away from delusional thinking.
Etienne Brisson from the Human Line Project says this kind of research is limited and that they had heard from people who’d had mental health spirals on these latest models too.
There is this BBC’s report released in May 2026. However, there are also Tim Hua’s experiment and the Spiral Bench (alas, neither of them is run on models after GPT-5.2) which imply that newer Western models are less sycophantic.
Additionally, I have heard that math journals regularly receive slop from users convinced by the AIs to the point thateven other AIs can see through it. Rhe criticism was ~one prompt away!Thanks! The two cases profiled seem to both be from last year (August of what’s presumably 2025 for Adam, April 2025 for Taka). But it does mention that