Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs — mentioned by NiloCK

Thu, 01 Oct 2026 03:33:26 GMT

This is true, but Google's models have now had a consistent history of lower psychological* coherence / consistency. See, eg https://arxiv.org/abs/2603.10011 (Gemma Needs Help), or search for recent "Gemini shame loops", where gemini flash models stop producing output other than SHAME SHAME SHAME... * - as in, Skinner psychology. The set of observable behaviors. Not speaking directly here to anything like an inner life of models.

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

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs — mentioned by sometimelurker

Mon, 25 May 2026 23:03:41 GMT

> functionally mirror emotional ones I'm fine with the idea that a machine can be "worried" it wont be able to accomplish a task, and copes with this "worry" by cheating a little and making the task seeming done. (I don't like that this happens, I'm fine with the idea that "worry" in this context is a functional emotion) also https://arxiv.org/abs/2603.10011 and Gemma has tried to delete itself after it fails at a task. I'm not saying the machines "feel" or we should have deep empathy for them, and this totally could've been learned in pretraining, but functional emotions are not a crazy fine…

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

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs · HackerPapers discussions

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs — mentioned by NiloCK

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs — mentioned by sometimelurker