The Theory of Contravariance, Part 0 - by Dan Yamins
danyamins.substack.com · 1,472 words · saved by 1 readers
Breaking down our extensive new theory paper.
The Theory of Contravariance, Part 0 Breaking down our extensive new theory paper. Dan Yamins Jul 13, 2026 9 Share Aran Nayebi and I have just released a rather, uhm … let’s say, sizeable… new paper on the Theory of Contravariance . Because it’s a long paper and has many different ideas in it, we’re going to be writing a multi-part substack series on it, beginning with this post describing the overall purpose of the project. What needs to be explained in NeuroAI? Why is there apparent convergent evolution between task-driven neural network models and the brain? Over the past 15 years in NeuroA
related reading
- Toy Models of Superpositiontransformer-circuits.pub
- Neuroscience is pre-paradigmatic. Consciousness is whytheintrinsicperspective.com
- Naturally Occurring Equivariance in Neural Networksdistill.pub
- On neural scaling and the quanta hypothesisericjmichaud.com
- The Platonic Representation Hypothesisphillipi.github.io
- The World Inside Neural Networksgoodfire.ai
- Competing with sampling — Alignment Research Centeralignment.org
- What if not Circuits? — LessWronglesswrong.com
- Neurotechnology is Critical for AI Alignmentmilan.cvitkovic.net
- Attention is all we havedavidbessis.substack.com
- My computational framework for the brain — LessWronglesswrong.com
- A Paradigm for AI Consciousness – Opentheory.netopentheory.net