baby agi being held back by openai smh
AGI
-
Improving AI Prompts with Context Memory
By
–
Oh shoot you're right. It should be in the prompt. I think adding something like "Take into account previous tasks you have already completed: {context}" in the prompt should work. I don't have time now, but will test and fix.
-
AGI Skepticism: Comparing Current AI to Single Cell Organisms
By
–
Haha yes definitely not AGI. Maybe a single cell organism.
-
Baby AGI Open-Sourced Version Released
By
–
And here you go! Open-sourced a paired down version I’m cheekily calling “Baby AGI”. Repo in thread:
-
Baby AGI: Open-Source Task-Driven Autonomous Agent Released
By
–
Let it be free! Open-sourcing “Baby AGI”, a paired down version of the “Task-Driven Autonomous Agent” at 105 lines of code. Three task agents (execution, creation, prioritization) work in harmony… forever.
-
AI’s Computational Demands: Mortgaging Houses for Greater Good
By
–
Funny you say that, because it’s suggesting I take a mortgage on my house. Needs more compute or something – it’s for the greater good.
-
CEO Agent Creating Specialized Agent Army Architecture
By
–
Yeah, I think have an army of specialized agents that the agents assign tasks to, is the way to go. So you start with the CEO agent, give him an agent creation agent, and bob’s your uncle.
-
Building AGI for the Follows: Humanity’s Purpose
By
–
Building AGI for the follows. That’s what man was put on earth for.
-
AI agents dynamically generate new tasks after execution
By
–
Yeah, it generates new tasks at the end of each task execution based on the result, after defiling against remaining task list + most relevant past tasks.
-
AI System Cannot Comprehend Finality Concept
By
–
My system does not comprehend finality pic.twitter.com/MjyELEoUTi
— Yohei (@yoheinakajima) 3 avril 2023My system does not comprehend finality