Opening the archive
Everything published here so far. Filter by topic, or sort by what gets read most.
In one month a restricted Claude model scanned over 1,000 open-source projects and isolated more than 10,000 high or critical severity bugs.
Tokens, vectors, attention, and next-token prediction. What is actually happening underneath something that feels like a conversation.
High test accuracy is meaningless if a model exploits spurious correlations. How cooperative game theory and local linear surrogates bring mathematical interpretability to deep learning.
Despite the name, it is a classification algorithm. It models the probability of a binary outcome from one or more predictor variables.
A supervised algorithm that models the relationship between your features and a target, on the assumption that the relationship is a straight line.
What the registration of genai.apple.com signaled: on-device 3B foundation models, the Apple Neural Engine, and the verifiable security of Private Cloud Compute.
735 views
728 views
683 views
356 views
