I’ve been working for some time now with a team inside of Microsoft on various ideas in the direction of more stable, longer-running agents based on LLMs, that use memory and other techniques keep context and perform more complex tasks, or even just maintain relationships with people (which is pretty wild).
Share this post
Intelligence and combinatorial complexity
Share this post
I’ve been working for some time now with a team inside of Microsoft on various ideas in the direction of more stable, longer-running agents based on LLMs, that use memory and other techniques keep context and perform more complex tasks, or even just maintain relationships with people (which is pretty wild).