UPIR: What If Distributed Systems Could Write (and Verify) Themselves?
Lessons from building a framework that automatically generates verified distributed systems - and why I think formal methods, synthesis, and ML need to work together
I Trained Probes to Catch AI Models Sandbagging
First empirical demonstration of activation-level sandbagging detection. Linear probes achieve 90-96% accuracy across Mistral, Gemma, and Qwen models. Key finding - sandbagging representations are model-specific, and steering can reduce sandbagging by 20%.
