Skip to content
a16za16z

Why Scale Will Not Solve AGI | Vishal Misra - The a16z Show

Vishal Misra returns to explain his latest research on how LLMs actually work under the hood. He walks through experiments showing that transformers update their predictions in a precise, mathematically predictable way as they process new information, explains why this still doesn't mean they're conscious, and describes what's actually required for AGI: the ability to keep learning after training and the move from pattern matching to understanding cause and effect. Timestamps 00:00 — Introduction 02:58 — LLM as Giant Matrix 08:24 — What Is In-Context Learning 13:00 — Bayesian Updating as Evidence 19:13 — Bayesian Wind Tunnel Tests 27:22 — Brains Simulate Causality 36:34 — Manifolds and New Representations 42:17 — Simulation as Short Program Read the full transcript here: https://www.a16z.news/s/podcast Resources: Follow Vishal Misra on X: https://x.com/vishalmisra Follow Martin Casado on X: https://x.com/martin_casado Stay Updated: If you enjoyed this episode, be sure to like, subscribe, and share with your friends! Find a16z on X: https://twitter.com/a16z Find a16z on LinkedIn: https://www.linkedin.com/company/a16z Listen to the a16z Show on Spotify: https://open.spotify.com/show/5bC65RDvs3oxnLyqqvkUYX Listen to the a16z Show on Apple Podcasts: https://podcasts.apple.com/us/podcast/a16z-podcast/id842818711 Follow our host: https://x.com/eriktorenberg Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see http://a16z.com/disclosures.

Vishal MisraguestErik Torenberghost
Mar 17, 202646mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 1:04

    Consciousness claims, and an “Einstein test” for AGI

    Misra opens by arguing that today’s LLMs—despite impressive products—are “grains of silicon doing matrix multiplication,” lacking consciousness or an inner monologue. He proposes a stringent AGI benchmark: train on pre-1916 physics and see whether the system can derive relativity from clues alone.

    • LLMs as powerful tools but not conscious agents
    • Why inner experience/monologue is not implied by fluent text
    • AGI bar: rediscover relativity from pre-relativity knowledge
    • Sets up skepticism that “scale alone” yields AGI
  2. 1:04 – 3:18

    From early GPT-3 experiments to deploying proto-RAG at ESPN

    Misra recounts getting early access to GPT-3 and using it to translate natural-language cricket-stat queries into a database-queryable format. This became a real production deployment at ESPN/Cricinfo, and the success motivated his deeper effort to mathematically explain why it worked.

    • Cricket stats querying as the motivating real-world problem
    • Few-shot prompting + retrieval to map English → structured queries
    • Practical constraints (small context window, productionization)
    • Curiosity shift: from “it works” to “why it works”
  3. 3:18 – 6:16

    LLM as a gigantic prompt→next-token probability matrix

    He introduces a simplifying abstraction: imagine an enormous matrix where each row is a prompt and each column is a probability over the vocabulary for the next token. This view clarifies generation as sampling from a posterior distribution conditioned on the prompt.

    • Rows = all possible prompts; columns = probabilities over tokens
    • Next-token distribution as the model’s posterior
    • Example: “protein” branching to “shake” vs “synthesis” changes future
    • The true matrix is astronomically large, so models compress/approximate it
  4. 6:16 – 8:25

    Why the giant matrix is compressible: sparsity and approximation

    Misra explains why the conceptual matrix is still workable as an abstraction: most token sequences are gibberish (row sparsity), and for any prompt only a small set of next tokens matter (column sparsity). LLMs effectively learn a compressed representation to approximate these distributions.

    • Combinatorial explosion from vocabulary size and context length
    • Natural language occupies a tiny fraction of possible prompts
    • Most next-token probabilities are near-zero for any given prompt
    • Training yields a compressed approximation of the sparse “true” matrix
  5. 8:25 – 13:00

    What in-context learning is, and the cricket DSL demonstration

    The conversation defines in-context learning as learning a task “on the fly” from examples in the prompt. Misra’s cricket DSL story shows GPT-3 completing a format it had never seen by conditioning on a few retrieved examples placed in the context window.

    • In-context learning: task induction from examples in the prompt
    • Custom DSL not present in training data
    • Semantic retrieval selects best few examples under context limits
    • Model completes new query in the unseen DSL within a single session
  6. 13:00 – 15:31

    In-context learning as Bayesian updating (empirical evidence)

    Misra describes how next-token probabilities shift toward DSL tokens as the model sees more examples, culminating in near-certain correct completion. He interprets this as Bayesian updating: a prior belief over continuations updated by evidence in the prompt.

    • Probability mass moves from English continuations to DSL tokens
    • Each example acts as evidence that reshapes the posterior
    • Bayesian framing: prior → posterior via observed context
    • Initial paper: strong empirical signs but not a formal proof
  7. 15:31 – 16:34

    Backlash to the Bayesian framing and the need for a formal proof

    They discuss why some researchers resisted calling LLM behavior “Bayesian,” partly due to Bayesian vs frequentist cultural battles and concerns that “anything can be called Bayesian.” Misra concludes that convincing skeptics requires a mathematical, not just empirical, demonstration.

    • Community reaction: “anything can be Bayesian” criticism
    • Bayesian vs frequentist camps influence interpretation
    • Empiricism wasn’t enough to satisfy skeptics
    • Motivation for a rigorous testbed and proof
  8. 16:34 – 19:13

    TokenProbe: peering into probabilities and entropy

    Misra explains building TokenProbe to visualize next-token probabilities and entropy after OpenAI removed probability displays. The tool supports open-weight models and became both a research instrument and teaching aid for understanding LLM behavior.

    • TokenProbe enables inspecting token probabilities and entropy
    • Prompt-level visualization helps build intuition for model updates
    • Built for open-source/open-weights models
    • Used in courses where students create and test their own DSLs
  9. 19:13 – 21:35

    The “Bayesian wind tunnel”: isolating mechanisms across architectures

    To prove Bayesian behavior, Misra and colleagues create controlled tasks where memorization is impossible, yet the exact Bayesian posterior is analytically known. Testing multiple architectures shows transformers match the posterior extremely closely, with a performance taxonomy across model types.

    • Wind-tunnel idea: controlled environment like aerospace testing
    • Tasks designed to prevent memorization (combinatorially large space)
    • Transformers match Bayesian posterior to ~1e-3 bits accuracy
    • Mamba performs well; LSTMs partial; MLPs fail
  10. 21:35 – 23:02

    Why transformers do it: geometry shaped by gradients, and scaling signatures

    Misra summarizes follow-on papers: one explains *why* transformers implement Bayesian updating by analyzing gradients and emergent geometry. Another shows similar geometric signatures persist in larger frontier models, though noisier due to diverse training data.

    • Second paper: gradient dynamics induce geometry enabling Bayesian updates
    • Third paper: signatures persist in larger open-weight LLMs
    • Production models look messier due to mixed data/skills
    • Core claim: Bayesian inference arises from architecture mechanisms
  11. 23:02 – 27:24

    Humans vs LLMs: plasticity, objectives, and why “deception” is data-driven

    Misra contrasts human lifelong synaptic plasticity with frozen LLM weights during inference; LLMs update beliefs in-context but do not retain learning across sessions. He argues apparent “self-preservation” behaviors reflect training data, not an intrinsic objective like biological survival.

    • Humans retain learning; LLMs forget after the context resets
    • Different optimization objectives: survival/reproduction vs next-token prediction
    • Plasticity as a missing ingredient for AGI
    • Alignment-like behaviors can be artifacts of data and prompting
  12. 27:24 – 31:06

    From correlation to causation: simulation, Pearl’s hierarchy, and pi as an analogy

    Misra argues deep learning largely captures associations (correlations) but not interventions or counterfactuals that require causal models and simulation. He links this to Shannon entropy vs Kolmogorov complexity, using digits of pi to illustrate how a short generative program can exist despite high predictive entropy.

    • Pen-throw example: humans simulate rather than compute token-like probabilities
    • Pearl’s hierarchy: association → intervention → counterfactual
    • Deep learning excels at correlation; lacks true causal intervention/simulation
    • Shannon entropy vs Kolmogorov complexity: predicting pi vs generating it via short code
  13. 31:06 – 36:34

    Why scale won’t solve AGI: continual learning + new representations (Einstein)

    Misra claims ‘scale will not solve everything’ and identifies two requirements for AGI: real plasticity via continual learning and a shift from correlation to causation. He revisits the Einstein test, arguing that discovering relativity required inventing a new representation/manifold—not just fitting correlations to existing data.

    • Continual learning is hard due to catastrophic forgetting risks
    • AGI needs (1) plasticity and (2) causal modeling/simulation
    • Einstein’s leap: a compact new theory (short description) explaining anomalies
    • LLMs exhibit ‘data gravity’: majority patterns overwhelm anomalous evidence
  14. 36:34 – 44:26

    Manifolds, Knuth’s result, and why humans still supply the Kolmogorov leap

    They frame LLMs as learning a manifold of human-written knowledge and performing Bayesian updates within it, but struggling to generate entirely new manifolds/representations. Knuth’s recent example is interpreted as LLMs doing efficient ‘Shannon’ search while the human provides the ‘Kolmogorov’ compression into a new proof/structure.

    • LLMs navigate learned manifolds; inventing a new manifold is the missing step
    • Knuth used iterative attempts + memory updates (a hacky plasticity)
    • LLMs find connections with compute; humans consolidate into new representations
    • Research direction: mechanisms for causal simulation and continual learning
  15. 44:26 – 46:48

    Where the research goes next: toward causal mechanisms beyond today’s LLMs

    Misra closes by outlining two parallel agendas: implementing plasticity safely and building causal models grounded in Pearl’s framework. He expects LLMs to remain part of the solution, but believes an additional mechanism is required to move beyond Bayesian correlation-based inference.

    • Next steps: plasticity/continual learning and causal modeling
    • LLMs are necessary but insufficient for ‘next-level’ intelligence
    • Pearl’s do-calculus and causal hierarchy as a guiding theory
    • Goal: move from understanding limits to designing new architectures

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.