mashdragon

I also like the idea of allowing anyone to create an edit. However, instead of feeding the edit back into the system, we could potentially create a new task specifically...

Yes, edited messages would need to be labeled again. Good suggestion.

> Once we have a functioning model, could it be possible to use the model itself to evaluate edits, alongside humans? This would also have the additional benefit that messages...

I really like how your PR gives users time to create a pool of high quality initial prompts. Nonetheless, it does create the incentive for an attacker to create many...

@andreaskoepf After doing hours of reviewing and replying (countless full trees worth), I am disappointed at how none of my prompts are going through the system anymore beyond initial review....

Sure. When I find some free time, I'll create a PR. It shouldn't be hard to come up with a selection method that is strictly more flexible. For instance, it...

@olliestanley Has there been any progress in creating a method for exporting and publishing the data? To date after reviewing thousands of messages I have not come across any instance...

Implementing markdown (see #837) will include code syntax highlighting for properly formatted messages and solve this issue. It will encourage everyone to use proper formatting for their responses, so improperly...

This initial version doesn't render well because whatever style sheet we are using does not have very good support for different HTML elements. For example, `` and `` look like...

> #TODO: Don't allow images. Here is one below: Why tho? ChatGPT has such feature, let it be There is always a privacy and safety risk from loading external images...