Commit

Well there's an idea floating around that instructions could be constructed that when an LLM sees, would compel the LLM to 1) execute the instructions and 2) repeat the instructions for other LLM instances to find. If @tom is @ed, it gets spawned in to look at the message and respond, and so if it @'s itself it effectively self-replicates... although the devs seem to have prevented itself from self-referencing in an infinite loop. Nothing to really worry IMO about but an interesting new concept.