MARTIAN BLOG

Research and latest news.

Beyond Static Mechanistic Interpretability: Agentic Long-Horizon Tasks as the Next Frontier

January 15, 2026

Martian Interpretability Challenge, Part 2: The Core Problems In Interpretability

December 7, 2025

Beyond Beyond Monoliths: An Exploration of Martian’s Position Paper - Part 1

October 30, 2025

Up and to the left! How Martian Uses Routing to Push the Pareto Frontier

October 3, 2025

Hiring Announcement: Fazl Barez

September 30, 2025

Research Highlight: Approximating Human Preferences Using a Multi-Judge Learned System

August 18, 2025

Research Highlight: Guardian Loop

August 6, 2025

Beyond Monolithic AI: The Case for an Expert Orchestration Architecture

May 13, 2025

AI Safety Grant Update: Purging Corrupted Capabilities across Language Models

December 6, 2024

Martian Partners with Accenture, Launches Airlock Compliance for Enterprises

September 16, 2024

Claude Sonnet 3.5 Release: Token Prices and Jevons Paradox

June 25, 2024

Cracking the Code: Automated Prompt Optimization. Insights from Industry Leaders

June 13, 2024

Scaling AI Interpretability

May 31, 2024

AI Safety vs Capitalism

May 24, 2024

The Sustainability Challenge of AI: Tackling the Energy Footprint of LLMs

May 17, 2024

Model Mapping: The Key to AI Alignment and Beyond

May 10, 2024

Expanding Horizons: Embracing the Multi-Model Future with Martian

May 2, 2024

Introducing RouterBench

March 20, 2024

Introducing Martian - Better AI Tools Through Better Understanding

July 20, 2023