On: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

[bartimus]

When asking about Taiwan and Russia I get pretty scripted responses. Deepseek even starts talking as "we". I'm fairly sure these responses are part of the model so they must have some way to prime the learning process with certain "facts".

[ExtraEmpathy → bartimus]

Using some old tricks that used to work with gpt but don't anymore I was able to circumvent pretty much all censoring

https://i.imgur.com/NFFJxbO.png

So I'm finding it less censored than GPT, but I suspect this will be patched quickly.