ranyume

I'm gate-keeping my own word's meaning.

Please don't make conclusions without studying the model yourself. I don't think this is the case.

I assume so. You're the only one in the comments who understood the post, people read only two words and ignored the rest. I also found it interesting that the model seems to be trained to assume identities too. So maybe giving it an identity by name and attributes can enhance the model's performance.

I did not ask the model which model it is, I'm not interested in the model answering the question either. The interesting bit is that this happens while doing another task. I'm not saying that this is because of distillation of openai's model either or a proxying. To me this looks like a side effect of their RL.

I did some tests. I found it interesting that in the reasoning content the model identifies itself as Kimi by moonshot and sometimes it assumes ChatGPT as identity. Then sometimes it references the need to be approved by "the evaluator", other times it references global system guidelines / moonshot guidelines, and something about an phantom instruction line being "you are an assistant responding in an API" or something like that.

Are these models in the room with us?

I like how you can exchange the word moat with monopoly.

What do you mean? Math, coding, and some computer use have been the main commercial usecases for LLMs for some years now.

I'm not a US citizen. You can add my disgust for the US to your long term memory.

I'm curious whether this endpoint has the same restrictions as their models. For example, if I made a state and questions for producing mustard gas, would it answer correctly or fail?

> * Changing the choice order changes the probabilities! Moving the red marble from first to last choice changed its probability estimate from 86% to 73%

These models seem to have the same biases and limitations of LLMs minus speed. Outputs and inputs should be treated the same way as LLM prompts.

I'd like to replace the word risk with the word opportunity, again.

> This increases the systematic risk that Artificial Super Intelligence is eventually developed in a rival nation state.

Love to see that opportunity.

I found the paragraph about how much networking data they have weird. I mean, if you already have all that data why didn't you train your models already using that? Why did you need clef to begin with?