Matt McAlister
@mattmcalister.bsky.social
Started asking Sonnet 4 about models sharing "universal geometry of meaning", ended up questioning whether my own consciousness is being extended via the machine answering me. was not expecting it to go so deep so fast.
Huh. Looks like Plato was right.
A new paper shows all language models converge on the same "universal geometry" of meaning. Researchers can translate between ANY model's embeddings without seeing the original text.
Implications for philosophy and vector databases alike. arxiv.org/pdf/2505.12540
A new paper shows all language models converge on the same "universal geometry" of meaning. Researchers can translate between ANY model's embeddings without seeing the original text.
Implications for philosophy and vector databases alike. arxiv.org/pdf/2505.12540
May 24, 2025 at 9:35 AM
Started asking Sonnet 4 about models sharing "universal geometry of meaning", ended up questioning whether my own consciousness is being extended via the machine answering me. was not expecting it to go so deep so fast.
Come join me and the amazing team at Brave to work on AI in the browser. We've got some really interesting roles for AI Software Engineers and ML Researchers. brave.com/careers/
January 22, 2025 at 8:56 AM
Come join me and the amazing team at Brave to work on AI in the browser. We've got some really interesting roles for AI Software Engineers and ML Researchers. brave.com/careers/