Notes on AI, math, and the long road. Live slow, die whenever.https://tahabouhsine.com/https://tahabouhsine.com/attention-is-a-kernel/https://tahabouhsine.com/attention-is-a-kernel/A reading of self-attention through kernel smoothing and RKHS.Thu, 14 May 2026 00:00:00 GMThttps://tahabouhsine.com/not-all-infinities-are-equal/https://tahabouhsine.com/not-all-infinities-are-equal/The singularity structure of cross-entropy explains hallucination, the modality gap, and why contrastive losses need such big batches.Mon, 23 Feb 2026 00:00:00 GMThttps://tahabouhsine.com/opposite-is-not-different/https://tahabouhsine.com/opposite-is-not-different/The cosine-similarity scale has three landmarks, not two. Maximum difference is orthogonality, not opposition — and the most influential contrastive losses spent years optimizing for the wrong target.Sun, 22 Feb 2026 00:00:00 GMThttps://tahabouhsine.com/activations-are-bad-for-geometry/https://tahabouhsine.com/activations-are-bad-for-geometry/Pointwise activations factor into the layer's Jacobian as a diagonal modulation. The same modulation that buys selectivity destroys geometric structure on the data manifold.Fri, 20 Feb 2026 00:00:00 GMThttps://tahabouhsine.com/ai-illiteracy-pt1/https://tahabouhsine.com/ai-illiteracy-pt1/On Morocco, AI education, and the cost of staying behind.Wed, 22 Sep 2021 00:00:00 GMThttps://tahabouhsine.com/poem-0-1/https://tahabouhsine.com/poem-0-1/A short poem.Mon, 20 Sep 2021 00:00:00 GMT