alt Hacker NewsEU models are not, in fact, competitive with US or Chinese models.
And that's not how these things work. If you censor the model for one purpose, you will degrade it for others. We both know that the bureaucrats won't stop at either of those purposes. It's not in a censor's nature to walk away satisfied.
Mistral is competitive and useful.
And Anthropic is famous for putting guardrails on their models, and yet continue to lead.
We don't have to, and shouldn't have to, tolerate tools that easily produce csam or similarly undesirable output.