Discussion about this post

User's avatar
Drew Spartz's avatar

These are so good! My new favorite Substack. Keep it up.

Expand full comment
IntExp's avatar

It is a good start to release the System Prompt and Specs.

Much of the biases of LLMs come from RLHF and the quality of the fine-tuning data, not to mention different levels of sysprompts, like "role:dev" and the self-prompting of thinking models

Expand full comment
15 more comments...

No posts