101–110 of 135 posts
Does it mean Gemini 3 will be announced soon? I noticed these model announcements often happen at the same time..
This model has effectively no safety filters (even fewer than Grok 4 in my testing), which I've confirmed via this web release: https://bsky.app/profile/minimaxir.bsky.social/post/3m5u7gib... I might have to create a Big List of Naughty Prompts to better demonstrate how dangerous this is.
It is exhausting deciding which model to use on any given day.
Maybe we need an AI that picks which AI for us to use
> Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.
Earlier quoted context omitted.
Maybe we need an AI that picks which AI for us to use
https://openrouter.ai/openrouter/auto > Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.
Earlier quoted context omitted.
I think the issues with those cases do not hinge on the free access to information, nor do the correction of those cases hinge on the restriction of this information.
Ah, the “guns kill people” argument that’s only uttered in the country that’s consistently ranked in the top 3 countries with the most gun related deaths. You would have a point if your vision for a self regulating society included easily accessible mental healthcare, a great education system and economic safety nets. But the “guns kill people” crowd generally rather sees the world burn.
I am begging you to learn what “per-capita” means, and to not deceptively include self-inflicted deaths in your public-safety arguments: https://en.wikipedia.org/wiki/List_of_countries_by_firearm-r...
Earlier quoted context omitted.
Modern open source LLMs are still RLHFed to resist adversarial output, albeit less-so than ChatGPT/Claude. They all (with the exception of DeepSeek) can resist adversarial input better than Grok 4.1.
Is this not easy to take out/deactivate?
Quality of response/model performance may change though
There’s also nous research’s Hermes’ series of models, but those are trained on llama3.3 architecture and considered outdated now
Earlier quoted context omitted.
Ah, the “guns kill people” argument that’s only uttered in the country that’s consistently ranked in the top 3 countries with the most gun related deaths. You would have a point if your vision for a self regulating society included easily accessible mental healthcare, a great education system and economic safety nets. But the “guns kill people” crowd generally rather sees the world burn.
> the country that’s consistently ranked in the top 3 countries with the most gun related deaths I am begging you to learn what “per-capita” means, and to not deceptively include self-inflicted deaths in your public-safety arguments: https://en.wikipedia.org/wiki/List_of_countries_by_firearm-r...
https://en.wikipedia.org/wiki/List_of_countries_by_firearm-r...
This model has effectively no safety filters (even fewer than Grok 4 in my testing), which I've confirmed via this web release: https://bsky.app/profile/minimaxir.bsky.social/post/3m5u7gib... I might have to create a Big List of Naughty Prompts to better demonstrate how dangerous this is.
