better doing

The danger of overthinking.

This is a machine learning paper about Large Reasoning Models dropping the ball by way of overthinking. Does this apply to humans too? “ Our analysis reveals that simple efforts to mitigate overthinking in agentic environments — such as selecting […]

fun facts

What’s a one-hot?

Imagine you had a bunch of on/off switches and only one could be in the on position at a time. That group is a one-hot. It’s used in digital circuitry and more recently natural language processing and machine learning. ~ learn more

fun facts

The faces of liberals and conservatives consistently differ

Machine learning is at it again… “Political orientation was correctly classified in 72% of liberal–conservative face pairs, remarkably better than chance (50%), human accuracy (55%), or one afforded by a 100-item personality questionnaire (66%).” | learn more