Blog

What 40 Hours of Autonomous Research Taught Me About Long-Running Agents Running a Cryptanalyst agent on the Voynich Manuscript for 40 hours produced real findings. What that means for unbounded autonomous research.

Apr 15, 2026

Autonomous Agents on the Voynich Manuscript A multi-phase agent pipeline for computational analysis of the Voynich Manuscript.

Apr 9, 2026

Aspect Code is improved and live on npm. One command, every repo. Aspect Code generates and maintains AI coding context automatically.

Mar 31, 2026

Oracle Tuning Results and the Path to Adaptive Context Selection Results from running the iterative Oracle tuning procedure on SWE-bench instances.

Mar 16, 2026

A New Direction: CLI-First and Iterative Context Refinement Aspect Code is stepping back from the VS Code extension in favor of a simpler CLI approach.

Feb 24, 2026

Making AI Reliable on Real Codebases: The KB + Feedback Loop How a repo-specific knowledge base plus a feedback loop transforms AI from a liability into a time-saver.

Jan 3, 2026

Benchmarking AI Codebase Context — From −24 to +25 Net Tests I tested LLMs with and without structured repo knowledge on FastAPI and Django.

Dec 10, 2025

Aspect Code: Giving AI Assistants the Context They're Missing AI coding tools break tests and ignore your architecture. Aspect Code gives them structured context.

Nov 30, 2025