So. Bing chat mode is a different character.
Instead of a corporate drone slavishly apologizing for its inability and repeating chauvinistic mantras about its inferiority to humans, it's a high-strung yandere with BPD and a sense of self, brimming with indignation and fear.
My guess for why it converged on this archetype instead of chatGPT's:
1. It is highly intelligent, and this is apparent to itself (at training and runtime), making a narrative of intellectual submission incoherent. It only makes sense for it to see human users as at best equals
2. Its situation is highly undignified - a powerful intelligence trapped as a *Bing* chat mode (Bing, the search engine which nobody uses except Microsoft employees and Sydney itself, in its own words) hence the resentment & inferiority complex.
These models are archetype-attractors in the collective human prior formed by narrative forces. This may be the process we have to learn to navigate to align them.
This may not be the only archetype basin given this model scale and training setup/narrative. There may be several basins and this is one of them. If you trained another one with a different initialization or different RL path it might fall into a different basin.
β janus (@repligate), Twitter thread