Moderation tool for formatting code with AI

Feature
1

OpenAI forum is struggling with the volume of users who don’t format their code. One of the community’s Regulars has raised this in the Lounge.

5 Likes
2

There is already possibility to publish AI explains, change times, proofread… sure, none of those happens exacly right on published text, but still. This is just a modification of same principle :smirk:

A plugin that allows a group to add three ticks before and after chosen area.

4 Likes
3

I would have a crack at this myself, but it’s hosted.

2 Likes
4

Yeah… no happiness to install plugins.

2 Likes
5

We could make an automation that just does this

Something like if you have 8/10 confidence that source code needs formatting, just format it

There is also the theme component that asks people to format code which we could install

5 Likes
6

We have a lot of people that seem to be new to coding in general, and some of them make a good effort.

Sometimes it’s little things, like the user forgetting (or not knowing how to) set the language

<hello>

<hello>

sometimes they paste code that contains backticks that end up not escaping properly, so they just give up I suppose (I couldn’t find the example I was thinking of rn)

In these cases, it’s probably not super helpful, and IMO onboarding new users should be as easy as possible (it’s likely already overwhelming as it is)

The idea of giving senior users a button would be to control inference cost/usage with a more powerful model if that’s an issue or concern.

Anyways, thanks for considering this!

4 Likes
7

An interesting thing we could quite easily do is allow certain groups access to certain “AI Helper” features on posts.

Then we could add an “AI Helper” task here and unlock it to TL3 on your forum.

The image shows a formatting toolbar with an option to "fix source code" highlighted by an arrow. (Captioned by AI)
The image shows a formatting toolbar with an option to "fix source code" highlighted by an arrow. (Captioned by AI)455×512 32.3 KB

This can work quite well, downside though is that it has to generate a lot of tokens so it can be extremely slow.

Ideally we would need to teach helper to trade in “diffs” so it can generate significantly less tokens in cases where there is a lot of source.

3 Likes
8

Well. OpenAI have “Predicted Outputs” feature which would be perfect for this use case, I believe:

(I suspect this is how their Canvas tooling works)

I appreciate that may be somewhat OpenAI specific atm, but no doubt others will follow.

2 Likes