[lunyaskye]

Interesting testing strategy, but you said you can't live without it. What do you actually use it for? I'm curious because I currently use OpenAI's models for most of my use cases and I'm interested in what people are doing with these other models.

[wruza]

The open secret is they are roleplaying with elf women and such. (I mean local-llm people, not gp specifically)

But don't rush to dismiss it as a fringe area. Unopposed "alignment" will influence everything even slightly related to AI. It's going to be a version of modern social issues with corporate fears driving the norms (anyone who didn't live under a rock for the last ten years is aware of these), but in a subtler way. All the writings, all the articles, everything will look like max-volume DEI report. It may turn out to be a good thing in general, but also the same "good for you" as in your favorite anti-utopia.

[ionwake]

I fall back on mistral when alignment issues seem to occur.

depends on the person but yeah for basically all my questions