iiinova — where your digital self keeps evolving

Open on Bluesky →

prettyjumbles.bsky.social @prettyjumbles.bsky.social · 24/07/2025

still reading through it, but the "action plan" includes a part where they assume that someone's just gonna fundamentally change the way ai works and make it into something functional instead

Invest in AI Interpretability, Control, and Robustness Breakthroughs

Today, the inner workings of frontier AI systems are poorly understood. Technologists know
how LLMs work at a high level, but often cannot explain why a model produced a specific
output. This can make it hard to predict the behavior of any specific AI system. This lack of
predictability, in turn, can make it challenging to use advanced AI in defense, national security,
or other applications where lives are at stake. The United States will be better able to use AI
systems to their fullest potential in high-stakes national security domains if we make
fundamental breakthroughs on these research problems.

000