Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians · HackerPapers discussions

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians — HN submission

Wed, 30 Sep 2026 21:39:54 GMT

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians — mentioned by Topfi

Sun, 16 Aug 2026 12:56:01 GMT

Greatly varies by the model, but such a flat denial along with calling those with (verifiably accurate [0]) experiences which happen to be different from yours "the anti-AI crew" and just assuming they can't possible use LLMs and couldn't possibly have formed their opinions on evidence, well, says a lot. LLMs, even frontier models by major providers, still have no reliable internalised way to assess the accuracy of their output and they have, do and will continue to for the foreseeable future, lead people down paths they shouldn't [1], partly by their architecture and the limits of the…

Paper and discussion history. A mention is not an endorsement.

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians — HN submission

Wed, 01 Apr 2026 19:56:36 GMT

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians — HN submission

Wed, 01 Apr 2026 03:35:24 GMT

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

5 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.