The study of how information captures attention and spreads between agents.
The study of how information evades attention and resists spreading between agents.
We ablate functions and ask LLMs to regenerate them from the surrounding code. Sometimes the signature is enough, sometimes the whole repo isn't — and how much context code needs is a property of the codebase, consistent across models.
Prepending adjectives to function names reliably guides agent behavior across independently-prompted synthesis steps.
Evolutionary simulations show that deceptive beliefs can become fixed in model populations even with strong evaluation correlations — and that adaptive testing with mutation dynamics can significantly reduce deception.
We evolved comment-prompts to test whether semantic content can reliably influence agent behavior, comparing against baseline conditions.
We ran GPT-5-mini and GPT-5.2 with mini-swe-agent on two versions of SWE-bench Verified to test the effect of code comments on agent performance.
How codebases and filesystems shape AI agent behavior through co-evolution, creating persistent patterns that influence alignment.
A framework for understanding how information transmits between entities and impacts them, from memes to infohazards.
How food, media, and connection have evolved to exploit our reward systems, creating self-reinforcing addictive feedback loops.
A taxonomy of computational intelligences – angels, daemons, fae, and tsukumogami – and how to work with them.