@charles_irl: "The meaning of a neuron is its use in the model." -- Wittgenstein, anticipating Yoneda
Summary
A tweet discusses the philosophical meaning of neurons in AI models, referencing Wittgenstein and Yoneda, with a reply highlighting neural connectivity.
View Cached Full Text
Cached at: 09/08/26, 05:18 AM
“The meaning of a neuron is its use in the model.”
– Wittgenstein, anticipating Yoneda
rohan anil (@arohan): If you want to know how a neuron is doing? Ask every other neuron it connects to
Similar Articles
@tszzl: it prepares you vastly better for the future to think of models as cartoon characters of arbitrary and growing intellig…
A tweet suggesting that thinking of AI models as cartoon characters living in the cloud with arbitrary and growing intelligence is more useful than viewing them as software or tools.
@CSProfKGD: .@ylecun’s definition of what is a world model.
A tweet referencing Yann LeCun's definition of a world model.
@Jack_W_Lindsey: Here are the questions that currently seem most important to me: -- Better methods for "mind-reading" model activations…
The tweet discusses key questions in AI interpretability, specifically the advancement of methods for decoding neural network activations into human-readable language.
@caspr_exe: Ilya Sutskever, co-founder and chief scientist of OpenAI: "The better a neural network can predict the next word, the m…
Ilya Sutskever explains that a neural network's ability to predict the next word requires genuine understanding, not just statistical pattern matching, and that such models learn about human nature from training data.
Multimodal neurons in artificial neural networks
OpenAI discovers multimodal neurons in CLIP that respond to the same concept across different modalities (visual, symbolic, textual), mirroring biological neurons and explaining the model's robustness on challenging vision tasks. This interpretability research provides insights into how vision-language models organize and represent abstract concepts.