Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Evaluating LLMs on creative writing via reader usage, not benchmarks. Parent comment
Most of it has been fine-tuning (SFT/DPO/GRPO), but also a lot of prompting and adding steps between the user's prompt and the output
There are no comments on this comment yet.
Most of it has been fine-tuning (SFT/DPO/GRPO), but also a lot of prompting and adding steps between the user's prompt and the output