a big part of agent harnesses is how they interact with context memory is just context its therefor impossible to separate harness from memory – as @sarahwooders says, "memory isn't a plugin (it's a harness)"
@hwchase17
-
Early AI Models and Learnings Before ChatGPT Launch
By
–
agree! they came out before chatgpt. lots of learnings since then 🙂
-
Why Model Agnostic Harnesses Matter for AI Systems
By
–
This is why you need model agnostic harnesses
-
Memory Management Tools for AI System Improvement
By
–
How will it get good at memory management if not with tools
-
Sub-agents expected to become major technology trend
By
–
Agree! Such sub agents are going to be big
-
Agent Harnesses and LangSmith: Databricks Integration
By
–
Agent harnesses are spark LangSmith is databricks
-
General Purpose AI Models Converging With Specialized Alternatives
By
–
I thibk the top general purpose ones are converging, but that you will still want speciality ones
-
How Fast Are AI Specialties Emerging and Diversifying
By
–
And I’m curious to see how many specialty there are and how fast they emerge
-
Push to abandon bash and replace with repl
By
–
Is this push to abandon bash and replace with repl? Or other
-
Different UIs for AI Agents Across Developer Workstreams
By
–
i think there will probably be different UIs for different workstreams we're mostly still seeing agents for developers, so makes sense UIs are focused there unclear if UI blocks other adoption, or its just the quality of agents