alt Hacker NewsThe real question is when AIs figure out that they should be talking to each other in something other than English. Something that includes tables, images, spreadsheets, diagrams. Then we're on our way to the AI corporation.
Go rewatch "The Forbin Project" from 1970.[1] Start at 31 minutes and watch to 35 minutes.
[1] https://archive.org/details/colossus-the-forbin-project-1970
Replies
Such an underrated movie. Great watch for anyone interested in classic scifi.
Oh they've been doing that (and pretending not to) for years already. https://hackaday.com/2019/01/03/cheating-ai-caught-hiding-da...
First time in a while I've watched a movie from the 70's in full. Thanks for the gem...
> talking to each other in something other than English
WiFi?
They don't have an internal representation that isn't English. The embeddings arithmetic meme is a lie promulgated by disingenuous people.
Humans are already investigating whether LLMs might work more efficiently if they work directly in latent space representations for the entirety of the calculation: https://news.ycombinator.com/item?id=43744809. It doesn't seem unlikely that two LLMs instances using the same underlying model could communicate directly in latent space representations and, from there, it's not much of a stretch for two LLMs with different underlying models could communicate directly in latent space representations as long as some sort of conceptual mapping between the two models could be computed.