terataiijo··on GPT-OSS Reinforcement LearningI think you can train a model to decrypt an encrypted. My friend tried this only on like simple example tho. As long as we have the environment, we can do these things.
terataiijo··on Large Language Models as Optimizers. +50% on Big Bench HardWhat's the difference between text-bison and PaLM 2-L? I thought they were the same model?