Nobody knows what is going on inside a large model, and the interpretability pictures we can draw do not answer the only question that matters.

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Biology keeps turning up whole classes of things nobody knew existed, and that is what defeats attempts to model it. DLDerek Lowe19 Sept 2024
• Large language models do not think in words. KRKenneth Reitz18 Jun 2026
• Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew. RSRichard Sutton26 Sept 2025
• Models are enormous only because the internet is bad: most of that capacity does memory work, and a better dataset would need far less of it. AKAndrej Karpathy17 Oct 2025
• What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. JDJeff Dean30 Jul 2026

See this claim on the map