OK, I can partly explain the LLM chess weirdness now(dynomight.net)
467 points by dmazin | 419 comments
Dynomight blog post following up on why gpt-3.5-turbo-instruct plays chess well while other LLMs play poorly, testing several theories.
#instruction-tuning on Hacker News
3 stories tagged instruction-tuning, newest first.
Releasing 3B and 7B RedPajama(together.xyz)
336 points by antimatter15 | 96 comments
Together blog post announcing the release of 3B and 7B RedPajama-INCITE language models, including base, instruction-tuned, and chat variants.
Databricks Releases 15K Record Training Corpus for Instruction Tuning LLMs(github.com)
327 points by xatalytic | 85 comments
GitHub directory in Databricks' dolly repo containing the databricks-dolly-15k JSONL dataset of human-written instruction-following records for tuning LLMs.