LessWrong (Curated & Popular)

"Personality Self-Replicators" by eggsyntax

Published: March 17, 2026

Duration: 22:19

One-sentence summary

I describe the risk of personality self-replicators, the threat of OpenClaw-like agents managing to spread in hard-to-control ways.

Summary

LLM agents like OpenClaw are defined by a small set of text files and run in an open source framework which leverages LLMs for cognition. It is quite difficult for current frontier models to self-replicate, it is much easier for such agents (at the cost of greater reliance on external agents). While not a likely existential threat, such agents may cause harm in similar ways to computer viruses, and be similarly challenging to...