Evaluating Language Model Agency through Negotiations

Language models are being used to create AI agents - by everyone. These “LM-agents” represent a remarkable paradigm shift away from one-shot tasks like question-answering and sentiment analysis. Suddenly, LMs have turned into dynamic decision applications, capable of planning and interacting over extended periods. In contrast, our evaluation methods have... [Read More]

So do you want to do research about YouTube...

The purpose of this blog post depends on the reaction you had while reading the question in the title. If you hesitated, I want to convince you that maybe you should be doing research about YouTube. If you are already interested, and I hope you are (always easier to preach... [Read More]