davidak

@emmahodcroft i usually say "write a blog post if you need more characters", but this makes a lot of sense. thanks for sharing!

I think a sane default would be to not show the same post again on the same day (or for 24 hours?) with an option to never show a post...

This is a complicated UX design problem. Most users probably only look up the package name and command to use with their default channel (e.g. nixos stable). Then the current...

...

@amitag2 i think it's not only asking about helpfulness. That would be a next step to be able to label it in more details. Maybe something like: "Please give us...

That would be pretty distracting. Don't have animations unless it is part of a user interaction as feedback.

There could be some animation to invite the user to provide feedback **once** after the answer is completed, so it can be seen as part of the answer showing up....

I suggest to close this in favor of https://github.com/LAION-AI/Open-Assistant/issues/2845 and don't use animations.

Today i thought of a cognitive architecture with a code generator model, then the code is tested if it runs (current Open Assistant code mostly don't) and code review ones...

>chatGPT is not able to put any proper evaluation of uncertainty about right or wrong of its responses I had the situation that i pointed out a mistake ChatGPT made...