Author
Tim Scarfe
By and about Tim Scarfe
Joscha Bach argues consciousness is a learning algorithm machines could find
Joscha Bach tells Machine Learning Street Talk that consciousness may be a simple learning algorithm a self-organizing machine could discover, and that today's language models are probably not conscious.
newsMLST: Mechanistic Interpretability - NEEL NANDA (DeepMind)
A deep dive with Neel Nanda on mechanistic interpretability: reverse-engineering neural networks, grokking, superposition, transformer circuits, world models, and why understanding model internals matters for AI safety.
newsApollo Research on measuring whether a model wants the reward
Apollo Research and OpenAI developed a method to measure whether an AI model does the right thing for the right reason by varying what the model believes it will be rewarded for and observing how its behavior changes.
newsMLST: AI is learning at the wrong level of abstraction
Physicist Matthieu Wyart argues deep networks succeed because real data has hidden hierarchies—parts within parts—and that predicting latent representations rather than raw tokens could make learning far more sample-efficient.