This was going to be my point as well. LLMs on their own probably aren’t there yet. But creative uses of in context learning can get you there. By having the LLM interact with the world in some way, judge it’s response against some objective, and then store the response and score in a vector db so that the next time the LLM encounters a similar scenario it can retrieve that example and use it to improve its response.
That process can take you a long way to AGI with tech we have today
This was going to be my point as well. LLMs on their own probably aren’t there yet. But creative uses of in context learning can get you there. By having the LLM interact with the world in some way, judge it’s response against some objective, and then store the response and score in a vector db so that the next time the LLM encounters a similar scenario it can retrieve that example and use it to improve its response.
That process can take you a long way to AGI with tech we have today