Cleaning up my perpetual agent 🙂 https://t.co/DsF3Q3LMLR
— Yohei (@yoheinakajima) 2 avril 2023
Cleaning up my perpetual agent 🙂
@yoheinakajima
-
Cleaning Up Perpetual Agent Architecture
By
–
-
Task Serialization and Parallel Execution for Process Optimization
By
–
You’re right. I need to create task serialization so we know what needs to be done before the next, which then allows for parallel tasks to be run. And then some milestones, and more reflection…
-
Framework Development with Programmatic Prompt Engineering Focus
By
–
100%. At this point, I’m focused on getting the framework working, then will improve on the task creation through some sort of programmatic prompt engineering ideas I have.
-
Perpetual Objectives vs Task Management in AI Systems
By
–
Agree. I’m trying to experiment more w perpetual objectives vs those with a closed end, so I think approach should be different than a novel. Though I still agree that task management needs an upgrade.
-
AI System Tackles Global Warming with Expanding Reasoning
By
–
Tried the objective: fix global warming
— Yohei (@yoheinakajima) 2 avril 2023
Still really cool to see it perpetually expand its thinking on this one topic.https://t.co/rvrgwnAOMRTried the objective: fix global warming Still really cool to see it perpetually expand its thinking on this one topic.
-
AI Solves Global Warming in Record Time with Safety Concerns
By
–
Oh, that's a fun one. Didn't quite let it get to wiping out humans (also, I need to work on memory better to reduce deduping after some time).
— Yohei (@yoheinakajima) 2 avril 2023
Objective: fix global warming (1 min 43 min) pic.twitter.com/mm6bYGtsATOh, that's a fun one. Didn't quite let it get to wiping out humans (also, I need to work on memory better to reduce deduping after some time). Objective: fix global warming (1 min 43 min)
-
World Interaction as Key Learning and Evolution Method
By
–
More or less, but being able to interact w the world is probably the best way to learn and evolve
-
LangChain Zapier NLA Integration Improves Reliability
By
–
for impressive, the langchain ZapierNLA connection allowed it to create a task list, search the web, and then write a report into google drive (though very unreliably) this version is not as impressive, but I can feel it becoming more stable 🙂
-
Simplifying AI Agent Architecture with OpenAI Text-Completion
By
–
Basically stripping it down to a barebones template only using OpenAI text-completion for all three task agents (execution, creation, prioritization). I think it makes sense to clean it up like this, and then add back on complexity – like Langchain, etc.
-
Task Management AI Agent Execution and Reprioritization Issues
By
–
It then continued to:
– execute tasks
– create new tasks
– reprioritize tasks Task mgmt agent is a bit wonky, so need to fix that… btw, all text-davinci-003 cuz… that's what i know