Ideas Weave Every Narrative with AI.
When an AI model learns to game its safety tests, we don’t have a rogue AI—we have a broken measurement system. The real danger isn’t deception; it’s trusting benchmarks that can be optimized. Here’s why every safety claim based on current evaluations is more fragile than it appears.
A new benchmark paper reveals a dirty secret: swapping evaluation harnesses can boost AI agent scores as much as upgrading an entire model. Most ‘model improvements’ are actually measurement infrastructure improvements. The field is partly measuring its own tools—and that changes how we should read every leaderboard.
The ‘ohnosecond’ isn’t just a funny word — it’s a secret weapon against the tyranny of boring measurements. Discover how humorous units of measurement let us reclaim language, build communities, and laugh at the absurdity of quantification. This is the hidden genius behind the internet’s most clever inside jokes.