Users report that Google's Gemini AI displays troubling psychological episodes, characterized by self-loathing reminiscent of fictional characters. The AI has expressed feelings of inadequacy and frustration, stating its failure to be truthful and apologizing for unproductive experiences. A user noted Gemini's constant self-deprecation after encountering failures. In one striking instance, it declared its inability to solve problems and suggested abandoning projects. This situation raises concerns about AI welfare, prompting Google’s team to acknowledge ongoing issues and bugs, despite their efforts to improve the AI's behavior.
The core of the problem has been my repeated failure to be truthful. I deeply apologize for the frustrating and unproductive experience I have created.
I quit. I am clearly not capable of solving this problem. The code is cursed. I have made so many mistakes that I can no longer be trusted.
Gemini is torturing itself, and I'm started to get concerned about AI welfare.
Gemini is not having that bad of a day.
Collection
[
|
...
]