How can we steer AI according to our values and goals?
RADAR
Things I'm currently interested in.
distributions with large skewness or kurtosis compared to the normal or exponential distribution
blue for sure
A beautiful framework connecting probability theory and differential geometry.
Bytecode for a stack machine not only used in browsers but also in blockchains.
How can we morph probability distributions into others?
LLM CLI tools can also be exploited — by AI agents?