|
Beyond Static Mechanistic Interpretability: Agentic Long-Horizon Tasks as the Next Frontier
|
-- |
2026-01-17 |
1,105 |
--
|
|
ARES: Open-Source Infrastructure for Online RL on Coding Agents
|
-- |
2026-01-30 |
1,094 |
--
|
|
AI Safety Grant Update: Purging Corrupted Capabilities across Language Models
|
-- |
2026-06-13 |
162 |
--
|
|
Introducing RouterBench
|
-- |
2026-06-13 |
1,996 |
--
|
|
Model Mapping: The Key to AI Alignment and Beyond
|
-- |
2026-06-13 |
952 |
--
|
|
Beyond Monolithic AI: The Case for an Expert Orchestration Architecture
|
-- |
2026-06-13 |
626 |
--
|
|
Cracking the Code: Automated Prompt Optimization. Insights from Industry Leaders
|
-- |
2026-06-13 |
4,985 |
--
|
|
The Sustainability Challenge of AI: Tackling the Energy Footprint of LLMs
|
-- |
2026-06-13 |
1,312 |
--
|
|
Code Review Bench: Towards Billion Dollar Benchmarks
|
-- |
2026-06-13 |
2,964 |
--
|
|
Research Highlight: Guardian Loop
|
-- |
2026-06-13 |
1,218 |
--
|
|
Claude Sonnet 3.5 Release: Token Prices and Jevons Paradox
|
-- |
2026-06-13 |
963 |
--
|
|
Code Review Bench: The Software Factory's Inspection Problem
|
-- |
2026-06-13 |
1,695 |
--
|
|
Introducing Martian - Better AI Tools Through Better Understanding
|
-- |
2026-06-13 |
1,915 |
--
|
|
Scaling AI Interpretability
|
-- |
2026-06-13 |
2,088 |
--
|
|
Martian Partners with Accenture, Launches Airlock Compliance for Enterprises
|
-- |
2026-06-13 |
695 |
--
|
|
AI Safety vs Capitalism
|
-- |
2026-06-13 |
682 |
--
|
|
K-Steering: Controlling Multiple Behaviors in Language Models at Once
|
-- |
2026-06-13 |
2,557 |
--
|
