Dwarkesh PodcastAdam Marblestone on Dwarkesh Patel: Why AI Uses Blunt Losses
Evolution-encoded cost functions give the amygdala a steering role; it labels cortex neurons with a per-stage curriculum that LLMs have no equivalent for.
At a glance
WHAT IT’S REALLY ABOUT
Why brains outlearn AIs: hidden loss functions and steering systems
- Adam Marblestone argues that current AI systems miss several fundamental ingredients that make biological brains sample-efficient, aligned, and flexible. He distinguishes between a "learning subsystem" (cortex-like, general world model) and a "steering subsystem" (subcortical, innate rewards and reflexes) and suggests evolution poured most complexity into the latter—especially rich, developmentally-timed cost functions. This architecture may support omnidirectional probabilistic inference, continual learning, and the robust wiring of abstract learned concepts (like social status) to primitive drives (like shame or fear). Marblestone also discusses amortized vs non‑amortized inference, neuromorphic hardware tradeoffs, formal methods in math and software, and a concrete roadmap for large-scale connectomics to ground AI and alignment in actual brain mechanisms.
IDEAS WORTH REMEMBERING
5 ideasBrains likely use many rich, evolution-designed loss functions, not a single simple objective.
Modern ML prefers mathematically simple losses like next-token prediction, but Marblestone argues evolution encoded a complex curriculum of region-specific, developmentally-timed cost functions that dramatically boost sample efficiency and shape what is learned.
A separate "steering subsystem" wires high-level learned concepts into primitive reward and reflex circuits.
Subcortical areas (e.g., hypothalamus, amygdala, superior colliculus) have diverse, genetically specified cell types and innate heuristics (e.g., spiders, faces, social status). Parts of cortex/amygdala learn to predict these signals, letting abstract features like “Yann LeCun being annoyed” trigger ancient emotional responses like shame or fear.
The cortex may implement omnidirectional probabilistic inference rather than one-way next-token prediction.
Instead of computing only P(next token | past tokens), cortical areas may approximate the joint distribution over many variables, allowing any subset of inputs to predict any other subset—supporting flexible cross-modal prediction (e.g., vision from audition, bodily states from language).
Understanding brain architecture means focusing on learning rules, cost functions, and connectivity, not decoding every neuron.
Marblestone suggests we should model the brain analogously to ML systems—by its architecture, learning algorithms, initializations, and training signals—rather than trying to interpret arbitrary learned microcircuits like “the Golden Gate Bridge neuron.” Connectomics becomes a constraint generator for such higher-level theories.
Neuroscience can realistically answer core AI questions if we invest billions in scalable tools like connectomics.
Technologies like optical, molecularly-annotated connectomes could drive the cost of a mouse connectome down from billions to tens of millions of dollars, enabling systematic mapping of learning vs steering subsystems across species within a decade if funded at low-billions scale.
WORDS WORTH SAVING
5 quotes“Evolution may have built a lot of complexity into the loss functions… a lot of Python code, basically, generating a specific curriculum for what different parts of the brain need to learn.”
— Adam Marblestone
“The steering subsystem has its own sensory system, which is kind of crazy… there’s a visual system with innate heuristics, and parts of cortex learn to predict those responses.”
— Adam Marblestone
“It’s kind of crazy that we don’t use value functions in LLMs… conceptually it’s a really dumb form of RL compared to what was being done ten years ago.”
— Adam Marblestone
“I want to describe the brain the same way we describe neural networks: architectures, learning rules, initializations, training data… not by finding the Golden Gate Bridge circuit.”
— Adam Marblestone
“If every iPhone was also a brain scanner, we would be training AI with brain signals.”
— Adam Marblestone
High quality AI-generated summary created from speaker-labeled transcript.
Get more out of YouTube videos.
High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.
Add to Chrome