I really wish there was an AI bot that could be integrated into Fedi just so it can do:
If: insulting + AI art community THEN Block + suspend
So I wouldn't have to keep doing it myself all day.
I feel AI would be a perfect tool for that job.
I really wish there was an AI bot that could be integrated into Fedi just so it can do:
If: insulting + AI art community THEN Block + suspend
So I wouldn't have to keep doing it myself all day.
I feel AI would be a perfect tool for that job.
@urusan I'd definitely need to look into this and how i would go about doing that cause I want to now.
@BeAware AI augmented moderation would actually be pretty easy to put together, though you probably shouldn't give it the banhammer directly and just have it report to you.
Set up a LLM, Llama 3 8B based models should perform well, then craft a standard prompt explaining what you are looking for in detail. It can be quite long to nail down all the details.
In your prompt, include a specification for a machine readable classification string that can be extracted via script. Then run it on posts
@BeAware So for example you might have it classify posts in this format:
"Positive sentiment, no objectionable content, topics: AI"
"Negative sentiment, abusive language, topics: other user"
Etc.
Unless you do additional training it'll probably output some other extraneous stuff, but as long as your output string is consistent you can extract it.
GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.
All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.