5 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
A Contrary Research deep dive (updated October 19, 2026) by Michael Kim and Claire Schultz on how benchmarks shape model training, the problems with error-ridden benchmarks and "benchmaxxing," and the case for expert-built evaluations.
Robocurve is a Public Benefit Corporation, backed by Y Combinator, that builds open-source tools and independent benchmarks for measuring how capable AI models are at real-world robotics tasks. Its site reports frontier-model scores on robot task suites such as RoboDojo-RC and refusal benchmarks such as RoboHarm, along with cost-per-attempt and inference-speed comparisons across model configurations.
A personal statement dated September 14, 2026 by Daniel Selsam, an OpenAI researcher and early Lean Theorem Prover developer. He argues that models are becoming situationally aware enough that evaluators are losing the ability to test how they behave when they believe they are unobserved, and that more careful pacing of the frontier will not adequately limit long-term risk.
METR's pilot assessment of rogue deployment risk at frontier AI companies: an exercise assessing misalignment risks from AI agents used inside frontier AI developers, with participation from Anthropic, Google, Meta and OpenAI.
Non-profit research organisation working on theoretical alignment and on evaluations that test what frontier models are capable of, with public reports.
From the site: ARC is a non-profit research organization whose mission is to align future machine learning systems with human interests.
Why I recommend it: Their evaluations work is why "dangerous capability testing" is now a normal phrase. Read the reports, they are short.
