Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)OP
Posts
159
Comments
2,674
Joined
5 yr. ago

  • All the models will have token limits, especially if you're not paying for API access. You would have to tune a model based on the blog posts, but that's expensive, degrades model quality, and isn't easy to do.

    Another thing you could do is have a model index the posts and then retrieve data based on search. The easiest way to do this would be download all the blog posts into a folder, then install cursor.com and open it on the folder. Cursor is for coding, but it will index your folder and then you can ask the model questions. You should be able to get this far with the free trial, but if you have a huge number of blog posts, it still won't work

  • It would be very unlikely to go well. I remember a case during the BLM protests where police were shooting at a random car, and the person in the car shot back. The police unloaded their clips - surprisingly no one got hurt.

    But specifically regarding the law, Stand Your Ground only works if there's an imminent threat to your body (getting arrested doesn't count). Basically, you would have to prove that you believed the ICE agent was going to severely hurt you to justify any severe harm to the agent. I'm not sure if there's many examples of ICE agents doing that

  • it's just that software isn't there yet.

    I put about 2000 hours of work into $open_source_project. After a huge release 10xing the quality, we had about 1000x as many users.

    The existing user base was ecstatic- for many of them, it was all they ever wanted and more. But we had 1000x new people saying "it just isn't there yet"