Research Agents

A deep dive into the Lean-backed pipeline where model output becomes papers, proofs, and formal checks, with the failures filed right alongside the wins.

A deep dive into the open-source SRE framework that pairs tool-rich incident response with stagnation detection, session memory, and a benchmark mindset.

Inside the system that replaces one-shot prompting with generational experiments, frozen evaluators, and evidence that compounds across rounds.

A deep dive into the Comparator pattern, the induction machinery behind singularity, and why this repo feels less like a paper and more like a verification pipeline.

How RLT turns token-by-token hidden state into a continuous reasoning loop, and why that changes the way we think about memory, depth, and long-context computation.

How a segment-then-prompt pipeline uses SAM2 and OpenCLIP to turn unlabeled orchard images into training data for lightweight detectors.

A MeTTa pipeline that turns frequent patterns into canonical identities, scores them by information-theoretic surprise, and feeds them back into a symbolic reasoning stack.

A local-first assessment app turns quiz answers into readiness scores, roadmap suggestions, and admin analytics without a real backend.