Thinking about LLM teams as distributed systems actually makes a lot of sense. Coordination, latency, and failure modes start to look very similar to traditional distributed architectures.
> Next up, LLMs as actors & processes in π-calculus.
You jest, but agents are of course already useful and fairly formal primitives. Distinct from actors, agents can have things like goals/strategies. There's a whole body of research on multi-agent systems that already exists and is even implemented in some model-checkers. It's surprising how little interest that creates in most LLM / AI / ML enthusiasts, who don't seem that motivated to use the prior art to propose / study / implement topologies and interaction protocols for the new wave of "agentic".
Thinking about LLM teams as distributed systems actually makes a lot of sense. Coordination, latency, and failure modes start to look very similar to traditional distributed architectures.
Next up, LLMs as actors & processes in π-calculus.
> Next up, LLMs as actors & processes in π-calculus.
You jest, but agents are of course already useful and fairly formal primitives. Distinct from actors, agents can have things like goals/strategies. There's a whole body of research on multi-agent systems that already exists and is even implemented in some model-checkers. It's surprising how little interest that creates in most LLM / AI / ML enthusiasts, who don't seem that motivated to use the prior art to propose / study / implement topologies and interaction protocols for the new wave of "agentic".
That's all nice & well but which protocol & topology will deliver the most dollars from investors?
Is it web scale?
Abstractly? 100%. Realistically? Depends on how many trillions we can get from investors.