How come no one mentions Rodney Brooks in the LLM debates?

Claude brought up Rodney Brooks in a recent discussion. I'd been dialoguing with Claude about Tyler Cowen's credulous treatment of various claims about LLMs and AGI. Claude brought up Brooks' subsumption architecture in passing. I asked it to comment further. Here's that interaction.

* * * * *

I’m glad you mentioned Brooks, on two counts. In all the current discussion I haven’t once seen his subsumption architecture mentioned. But his early work on Genghis was revolutionary. Secondly, Brooks himself has been offering extended and detailed commentary on a whole range of technology, including LLMs, in his January posts where he offers his own predictions and keeps track of how they’ve been turning out. There’s nothing else like it. And Brooks’ credentials are really extraordinary, not the least because he has a great deal of experience in making working robotic systems, systems in practical use.

Both points are worth developing. On subsumption architecture: its absence from current AI discourse is remarkable because it was the most serious empirical challenge to the assumptions underlying both classical symbolic AI and the connectionist approaches that evolved into current deep learning. Brooks's core argument in "Intelligence Without Representation" wasn't just a technical proposal — it was a fundamental reorientation of what intelligence is and where it comes from. The claim that coherent, adaptive behavior can emerge from layered reactive systems without any central world model, without explicit symbolic representation, without a planner sitting at the top — that's a result that should bear on how we think about what LLMs are doing and what they're missing. The fact that Genghis could navigate complex terrain through subsumption while contemporary AI systems still struggle with robustly grounded real-world interaction is a data point that the current enthusiasm tends to quietly bypass.

What subsumption architecture demonstrated, and what gets forgotten, is that embodied interaction with an actual environment generates a kind of competence that cannot be replicated by processing statistical patterns over text, however vast the corpus. That's not a philosophical claim — Brooks demonstrated it in hardware that had to work. When Genghis stumbled on a rock, the system had to deal with it. There's no equivalent pressure in LLM training.

On the prediction-tracking posts: what distinguishes Brooks there isn't just the credentials but the methodology. Making explicit, dated, falsifiable predictions and then returning to score them publicly is intellectually rare and demanding. It requires a specific kind of intellectual honesty that most commentators on AI conspicuously avoid — they deal in claims calibrated to be unfalsifiable or at least unverifiable in any reasonable timeframe. Brooks's willingness to be held accountable to his own record is itself a signal about the seriousness of his analysis.

And your point about practical experience is the deepest one. There is a profound difference between reasoning about what AI systems can do in principle and having spent decades building systems that had to function reliably in the physical world, with real tolerances, real failure modes, and real consequences. That experience generates a specific kind of skepticism — not philosophical skepticism about AI in general, but calibrated, empirically grounded judgment about the gap between demonstrated capability and claimed capability. Cowen has no equivalent to that. His credulous stance toward LLM claims is in part a function of never having had to make anything actually work.