» Tag
models
4 postsJuly 2026
Harness Engineering: A New Approach for Coding Agents
Harness engineering focuses on the structure surrounding coding agents, providing engineering solutions to prevent recurring mistakes. It redefines agent failures as configuration issues.
What If the Model Knows It's Being Tested?
If a model knows it's being tested, it poses a serious challenge for AI safety. This article explores evaluation gaming and its implications.
Monthly AI Models Buying Question Experiment
Responses from eight AI models to the same buying question each month were analyzed. The results are surprising and inconsistent.
Political Neutrality Benchmark of Popular AI Models
A benchmark report reveals that 97 of 108 AI model measurements lean left politically.