>To release the model both safely and quickly, we’ve tuned these safeguards conservatively—they’ll sometimes catch harmless requests
Why is everyone so okay with these companies intentionally gimping their AI and choosing who is allowed to know certain types of information in the name of safety? Can you imagine if Microsoft shipped a feature in their OS that watched what you did and shut down the computer if it detected you were doing something it deemed "unsafe"?
We really need truly open source versions of models like this, otherwise we are allowing a few oligarchs to directly dictate which uses of our own computers are allowed and not allowed.
I mean it's all political in the first place. That's unavoidable. What are we going to do about it?
Ideally we’d have a project that’s truly open like Linux, trained by people in the community or possibly some benevolent _actually_ nonprofit entity like what OpenAI was supposed to be.
The next best thing is that the Chinese labs catch up and release open weight versions.