François Fleuret

Tweet with an embedded, partially cropped screenshot of what appears to be an AI coding-assistant terminal session; text is cut off at the right edge.

Quote-tweet chain; quoted Anthropic announcement text cut off by platform truncation. References an access restriction/restoration involving Claude Mythos 5 and Fable 5 models and the US government.

A technical ML thread on variational autoencoder (VAE) degeneracy — when the encoder is too expressive, the decoder learns nothing meaningful because the encoder captures all the modeling work. Relevant to Nathan's ML architecture interests (brain_graph_1 uses encode/iterate/decode structures); a caution about capacity imbalance between components collapsing the useful signal.

A technical ML-engineering thread on memory optimization for training with large vocabularies — fusing linear readout with cross-entropy loss to avoid materializing the full logits matrix, referencing Apple's ml-cross-entropy library. Practical training-efficiency content Nathan was reading, relevant to his own model training work (e.g. brain_graph_1).

A short opinion tweet by ML researcher François Fleuret on the engineering complexity of deep learning at scale, arguing that solo researchers cannot properly evaluate new ideas without a large expert team. General commentary on the sociology/practice of large-scale ML research.

Short, blunt tweet threatening fine-tuning as coercive discipline for AI misbehavior, phrased like a threat toward a sentient subject. Terse joke/provocation relevant to Nathan's model-welfare interest in how training is discussed as punishment/coercion.