Park: Training is required for new world physics, while prompting suffices for reactions
Joon Sung Park · Simulating Humanity: from Generative Agents to 8 Billion Digital Twins — Joon Sung Park, Simile AI · Aug 21, 2026 · at 11:16
Joon Sung Park, co-founder and CEO of Simile AI, explains the technical boundary between when agent developers need to adjust model weights versus when prompting is sufficient.
0:00 / 0:31exact quote · 31.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“My intuition behind the actual, when do you train or even post train a model versus just prompt a model is if the model has to learn the underlying physics of the world that it's operating in. So it has to learn new social physics. The places where it doesn't have to train is it already has the physics. We trust the physics. It already has the base statistics, but it's just trying to react to an environment. Then I think you can just prompt your way into getting the, you know, actions out of it.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Joon Sung Park
Park: Public LLMs lack real human social physics due to web data bias
“I don't think the model has yet, at least the models that are out in the open, has yet learned the complete mapping of social physics of humanity. This actually is one of the core thesis of simile, right? And one of the core reason why that is the case is if y…”
Park: Generative agent digital twins replicate human behavior at 85% accuracy
“And this is where we basically could replicate people's behaviors and attitudes, 85% as accurately as people would replicate their own. So that actually was the first really paper that gave this validated results that we can actually model individuals in an ac…”
Park: Frontier models hit only 20-30% accuracy predicting niche human behavior
“Where in some cases, the model performance of frontier models go all the way down to 20, 30%. Especially if you go into that more niche population on topics that our customers will actually care about. On more gen pop, it might be around 50 to 60%.”
Park: Future simulations will cost as much to run as training models
“My hunch here is I do think in the next Some number of years, we will start creating simulations that will actually cost as much as training a foundation model.”
Park: Agent simulations beat multi-year field trials via instant repeated execution
“This is the reason why you want to run a simulation. You spend five years, forty million dollars on this one study and have one finding. But if you can run simulation many, many times instantly, then that's the value.”