New @ToolUsePodcast episode by @MikeBirdTech is live and I had the pleasure of being part of it alongside @karan4d from @NousResearch and three other great builders.
We went deep on Hermes Agent: self-improving skills, ambient agents, why the harness matters as much as the model, and why open source AI must win.
I got to share some @WolfBenchAI insights and real-world use cases. Give it a listen on Spotify or watch it on YouTube - links in reply.
I got to sit down and chat w/ my friend @MikeBirdTech & @ToolUsePodcast about the meta of what @Teknium and @NousResearch and @sudoingX have built with HERMES-AGENT
Some different perspectives from some different long, running agent builders here. Please check it out and make sure to check out the earlier versions of tool use. This is a really awesome podcast with some deep dives on some of the largest sort of archetype landmarks we've moved through into calling and extreme agentic abilities over the last couple of years and if you don't know, Mike, he is one of the core members of launched the open interpreter project, which was just literally miles ahead and on par with almost everything we're still doing today but w/ way better nodeps and harnesses... like hermes-agent
https://t.co/8DgxAgADwd
https://t.co/kvTQt2LjAm
How do I let my agent buy stuff?
Specifically, what are the open source options for giving an AI agent (doesn't matter which one[s]) access to a wallet or make payments in a safe way?
This week, we're diving into any-llm, a tool from @MozillaAI
Nathan Brake build any-llm and explains the different use-cases and benefits to a tool like any-llm.
- quickly switch between models with a single line code change
- test different models to see what will accomplish your goals
- robust evals to optimize your system
I like it! And we had a fun chat
Of course, it's fully open source
Stop over-complicating your RAG chunking. 🛑
If you’re spending days on custom agentic chunking logic before trying a simple paragraph split, you’re doing it wrong.
Senior Developer Advocate Arjun Patel breaks down the "Keep It Simple" framework for data prep:
📍 Wikipedia? Paragraphs.
📍 Textbooks? Sub-chapters.
📍 Multimodal PDFs? Page-by-page.
Check out the full conversation with @MikeBirdTech on @ToolUsePodcast that covers sparse/dense embeddings, reranking, Pinecone’s Claude Code plugin, and more: https://t.co/NKrpyOQo0f
How do you know if you need a vector database?
My coworker Arjun Patel gives you the answer and demos some easy ways to get started on the latest @ToolUsePodcast episode ⤵️
https://t.co/krB2IXiN6o
If you rent your AI, how long will you have a moat?
Max McCrea, founder of Greyhaven, joins us to talk about sovereign AI and how to architect systems for your business that maximizes data control.
This is a great chat for understanding the current state of sovereign AI and how you can implement it today
Want to make your own video or image model?
@gregschoeninger from Oxen AI walks us through how you can fine tune a model for your task (as cheap as $1!) and get outsized performance
Had a great chat about Fine-Tuning image/video models with @MikeBirdTech last week! He's got a great YouTube channel and podcast with some gold hidden in there if you haven't seen it yet.
https://t.co/c4aWnpUHEd