Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
predict-rlm: Recursive Language Models
Learn how Recursive Language Models avoid context rot by programmatically interacting with context via a REPL. See how to define DSPy signatures, wire up tools, and get structured outputs from multimodal documents.
predict-rlm is a callable RLM (Recursive Language Model) runtime built on top of DSPy. You define your inputs, outputs, and tools — the model handles its own control flow via a sandboxed REPL. I’ll demo how it processes documents (PDFs, images, invoices) end-to-end, showing how a single RLM call can recursively decompose complex tasks into sub-LM calls — with fully interpretable trajectories and structured outputs — all without context rot.