This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Caracter
caracter.bsky.social
did:plc:wzulhzhph2wtkf5c2psqwqph
in my mind(prob oversimplified): making a LLM is:
-Get training data
- Clean it
- Make the model try and predict next token base on preceding tokens. Reward when right. Repeat
- Tune the models to human preferences.
What part would pretraining of that be?
2025-07-23T11:34:12.044Z