Next up, LLMs as actors & processes in π-calculus.
robot-wrangler 10 seconds ago [-]
> Next up, LLMs as actors & processes in π-calculus.
You jest, but agents are of course already useful and fairly formal primitives. 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 interested in using the prior art to propose / study / implement topologies and interaction protocols for the new wave of "agentic".
timcobb 47 minutes ago [-]
Is it web scale?
measurablefunc 43 minutes ago [-]
Abstractly? 100%. Realistically? Depends on how many trillions we can get from investors.
Rendered at 19:58:37 GMT+0000 (Coordinated Universal Time) with Vercel.
You jest, but agents are of course already useful and fairly formal primitives. 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 interested in using the prior art to propose / study / implement topologies and interaction protocols for the new wave of "agentic".