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.
@yoheinakajima
-
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
-
Balancing AI Context Window Size and Summarization Strategies
By
–
It’s a balance of figuring out how much past context you want to pull in. If you pull zero, it stays within limit easily but no prev context. If you pull 5, you get decent context but it can get large. So then you can consider adding a summary step. pic.twitter.com/1jN3J8DMQI
— Yohei (@yoheinakajima) 3 avril 2023It’s a balance of figuring out how much past context you want to pull in. If you pull zero, it stays within limit easily but no prev context. If you pull 5, you get decent context but it can get large. So then you can consider adding a summary step.
-
AI-Generated TikTok Content Creation Strategy Discussion
By
–
Oh tight. Wait, should I start a Tik tok? Take requests and just post videos of the output.
-
Autonomous AI Agents Tackle AI Alignment Problem
By
–
I asked my autonomous AI to solve AI alignment.
— Yohei (@yoheinakajima) 3 avril 2023
Fascinating to watch.
Agents:
– Task execution: text-davinci-003
– Task creation: text-davinci-003
– Task reprioritization: text-davinci-003 pic.twitter.com/rmOnKIgaAzI asked my autonomous AI to solve AI alignment. Fascinating to watch. Agents:
– Task execution: text-davinci-003
– Task creation: text-davinci-003
– Task reprioritization: text-davinci-003 -
Removing Langchain as Default Execution Agent for Debugging
By
–
Yeah I’m working on a version that stripped out Langchain as default execution agent. Mostly for making debugging easier.
-
Python Framework Development and TypeScript Translation for AI
By
–
I guess that would be a one word change in the prompts I'm using. Python basic framework is close, then maybe I'll have ChatGPT translate to Typescript.
-
Relevant Context Management for Autonomous Agents
By
–
The thread broke, but here's a simple example of how "relevant context" (most relevant tasks from past) can be provided to current task. Allowing the autonomous agent to continue generating novel ideas and next steps – that wouldn't fit within a context window.
-
Balancing Context Length, Speed, and Cost in AI Systems
By
–
The decisions you need to make… – how much context you provide
– where/what/how you summarize
– how you break up knowledge
– etc. …are a constant balance of context length, model speed and cost, use case, latency, keeping up w latest tools, and more. -
Pinecone Vector Search Enhances Task Execution Memory
By
–
Added a new "Relevant Context" section that shows up in the "Task Execution" stage. This is to show how we're using @Pinecone vector search to provide memory from past tasks into the current task being executed. It's empty on step 1.