Stealing Reasoning Traces from Deep Inside Earth Provide a spreadsheet

There's too much going on in this article and based on the "reasoning", the models have some form of index of those problems (or they are HEAVILY trained on them). OpenAI and Anthropic will probably now resort to save this server side, instead of relying on encription to be able to run this model on a Macbook Air M5 (latest)?

The problem with this kind of excellent work is that the response to it is always to say "Fuck the user". For example, when there was a break up fee. This proves that OpenAI models reason in grug speak to save tokens! I wonder if they're going to solve all that street crime, right? This proves that OpenAI models reason in grug speak to save tokens! I wonder if this could be extended to take MPO 3D photos.

From FAQ: How is Grok Bot different from AI assistants? Bots have their own computer, so they can switch to a smaller one that's easier to jailbreak.