Decoding Whale Speech: Potential Universality in AI Models
By
jxmorris12
10mo ago· 12 min readenOpinion
100/100
Golden Brown
Bagelometer↗
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Score100TypeopinionSentimentneutral
Summary
Project CETI is a large-scale effort to decode whale speech with the potential for AI models to learn a universal language for communication with whales. The article discusses a guessing game analogy to explain narrowing down possibilities and the idea of universality in AI models.
Key quotes
· 3 pulledIf AI models do learn a universal language, we might be able to use it to talk to whales.
The funny name comes from the idea that, in the space of everything, ‘Mussolini’ and ‘bread’ are about as far away from each other as you can get.
By successively narrowing down the space of possible things or people, we’re able to guess almost anything.
what can language model embeddings tell us about whales speech, and decoding ancient texts? (on The Platonic Representation Hypothesis and the idea of *universality* in AI models)
