AI Safety Still Needs Great Engineers
Career essay arguing that AI safety needs strong software engineers to deploy safeguards like inference-time guardrails at scale, alongside alignment research. No technical results.
Research / Sources
Goodfire
Understanding and steering neural networks. goodfire.com
Focus All
Topic Trustworthy AI
Date Any time
Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
Makes resampling analysis of LLM reasoning uncertainty cheaper by smoothing low-sample rollouts, finding uncertainty dynamics converge to stable patterns so far fewer samples are needed.
Adversarial Examples Are Not Bugs, They Are Superposition
Argues that superposition is a primary cause of adversarial examples, using theory, toy models and ResNet18 experiments linking robustness training to superposition.