Edit ‘autogollark’

This commit is contained in:
osmarks
2025-05-10 10:29:02 +00:00
committed by wikimind
parent 309a4719ad
commit def2617c80

View File

@@ -22,7 +22,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
}
* {Tool capabilities (how to get the data? Examples in context only?!).
* Synthetic via instruct model.
* RL (also include reasoning, of course). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. https://arxiv.org/abs/2503.22828 would probably work.
* RL (also include reasoning, of course). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. [[https://arxiv.org/abs/2503.22828]] would probably work.
}
* {Local finetune only? Would be more tonally consistent but dumber, I think.
* Temporary bursts of hypercompetence enabled by powerful base model are a key feature. Small model is really repetitive.