SIEVE: Can an AI Data Center Hide Its Heat?
Exploring how an AI data center campus can be set up, how each setup gets rid of its heat, and how an outsider could detect it. Tested on real sites: thermal satellites did poorly, while counting equipment and reading permits worked far better.
Distillation Caltrops: Watermarks That Live in Learned Habits
Plant a useful reasoning habit in a teacher model. A distilled student inherits the habit form without the substance, fails confidently, and leaves a detectable fingerprint that survives paraphrase.
μInference: From Minimal Stack to SL5 Weight Enclave
Can frontier AI inference run on a radically minimized stack while protecting model weights against nation-state adversaries? An seL4-backed Weight Enclave prototype.
OpenWild: A New Conversational Dataset for Modern LLMs
A new conversational dataset for modern language models. Inspired by WildChat, capturing real-world interactions with current-generation systems.
Mechanistic Watchdog: Real-Time Cognitive Interdiction for LLMs
Real-time cognitive interdiction for LLMs. A safety layer that monitors internal activations and halts generation before harmful content is produced.