AIs can develop a lot of technical/cultural content with high serial depth, things like novel concepts and languages
Not sure you need continual learning for that …
Reasoning Models Sometimes Output Illegible Chains of Thought, Oct 2025
https://arxiv.org/pdf/2510.27338
activation vectors stop making sense
I’m not sure that’s true …
Unsupervised decoding of encoded reasoning using language model interpretability, Dec 2025
https://arxiv.org/abs/2512.01222v1
but I don’t think the experiment has been done for RL?
Not sure you need continual learning for that …
Reasoning Models Sometimes Output Illegible Chains of Thought, Oct 2025
https://arxiv.org/pdf/2510.27338
I’m not sure that’s true …
Unsupervised decoding of encoded reasoning using language model interpretability, Dec 2025
https://arxiv.org/abs/2512.01222v1
but I don’t think the experiment has been done for RL?