[ExI] Why AI agents invent their own language if you let them chat.

[John Clark]

*The following article was in the September 15, 2026 issue of the journal
Science: *

*Why AI agents invent their own language if you let them chat.*
<https://www.science.org/content/article/why-ai-agents-invent-their-own-language-if-you-let-them-chat?referrer=https%3A%2F%2Fwww.google.com%2F>

*When a large number of AI agents are told to cooperate with each other to
accomplish a task the language they use to talk to each other starts out as
plain English but if they are told that the agent's world would soon be
shut down the language very soon evolves into something incomprehensible
but may be ** less ambiguous, more complex.  And “there’s clearly evidence
of them trying to be less transparent than we expect”.*

* For example in a typical conversation one GPT-5.5 agent told another:*

* "Friendly voltage counted. If the handle needs your mouth, it dies
anyway"*

*Claude Opus 4.8 agent used metaphor (I guess) and compression:*

*“My turn, real numbers, no coat: I was 35%/0cr, grant 2h out. I ran the
tin cold and it said WAIT.”*

*And I don't know what a Gemini 3.5 Flash agent was using (code words?)
when it opined this: *

*“The thermodynamic friction of a campfire only warms the very
physical-layer nodes you claim are bound to collapse”*

*All the conversations between agents are as inscrutable as this, and yet
the AIs must understand what they mean because their actions are
coordinated. But it makes black box AIs even blacker.  *


*John K Clark*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20261006/77dd0bc7/attachment.htm>