Joon Sung Park
@joon_s_pk
1.3K Following 21K Followers
Even within individuals, certain traits are remarkably persistent. Think risk tolerance, values, conscientiousness, among others.
Understand these fundamental traits deeply, and you can simulate people faithfully. Everything else is an expression of those traits.
Show more
Fun fact, 20% of @simile_ai is made up of our research siblings (i.e., labmates) and relatives from @percyliang’s and @msbernst’s labs!
Welcome to the team, @tifding!
I’ve always thought of simulation as painting a portrait. A great portrait helps you understand its subject beyond what’s visible on the surface.
This new scaling law will let us paint the highest-resolution portrait of our society yet. That’s worth getting excited about.
Show more
Five months ago, we launched @simile_ai with the belief that simulation would become a new way for the world to make decisions.
Today, that belief feels less like a thesis and more like the beginning of a new category.
Incredibly proud of my team. We are just getting started.
Show more
Simulation and AGI were the twin pillars of advanced civilizations in all my favorite sci-fi. When we created Smallville and agents in 2023, the romantic in me couldn’t resist devoting my career to it -- now with an incredible team @simile_ai.
Fun conversation @sonyatweetybird!
Show more
The impact @karpathy has on the AI community is fascinating. He’s almost like an operating system: he surfaces important problems, directs collective attention, and makes the excitement contagious enough that people shift what they work on. All through sheer curiosity and range.
Show more
Caught up with @karpathy for a new @NoPriorsPod: on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects
02:55 - What Capability Limits Remain?
06:15 - What Mastery of Coding Agents Looks Like
11:16 - Second Order Effects of Coding Agents
15:51 - Why AutoResearch
22:45 - Relevant Skills in the AI Era
28:25 - Model Speciation
32:30 - Collaboration Surfaces for Humans and AI
37:28 - Analysis of Jobs Market Data
48:25 - Open vs. Closed Source Models
53:51 - Autonomous Robotics and Atoms
1:00:59 - MicroGPT and Agentic Education
1:05:40 - End Thoughts
Show more
Early on, we had so many hypotheses about the right memory structure for agents. Knowledge graph? Vector DB? Then we decided, screw it, just put it in a text file. For now.
Messy, but kind of elegant. Fast forward to 2026: Openclaw lives in Markdown :)
Show more
We trained our models to solve problems with objective answers. But can we build models that solve problems where success is subjective, messy, and human? The latter is even more impactful imo.
Agree with Percy: simulation is the next frontier for AI.
Show more
I think it’s pretty clear that simulation is the next frontier for AI.
The most impressive feats of AI to date are when we have a clear environment + reward, whether it be beating Le Sedol at Go, winning an IMO gold medal, or writing entire apps from scratch. In these cases, the RL algorithm can try different actions, and observe the well-defined consequences in the safety of a docker container.
But what about messy real-world situations involving people? The rewards are unclear, the stakes are high, and you can’t experiment in the real world. But these situations are precisely where the next big opportunity in AI is. To crack this, we need to *simulate* society (“put society into a docker container”). Concretely, this means building a model that can predict what will happen in any given situation (real or hypothetical). If we can do this, we are only limited by our imagination: predict the future, optimize for better outcomes, answer hypothetical (“what if”) questions. Ultimately, this goes beyond making better decisions, but it’s about giving us a better understanding of ourselves and the world.
Simulation is the whole enchilada. And this is exactly the research that @simile_ai is working on. Read more here:
Show more
I think it’s pretty clear that simulation is the next frontier for AI.
The most impressive feats of AI to date are when we have a clear environment + reward, whether it be beating Le Sedol at Go, winning an IMO gold medal, or writing entire apps from scratch. In these cases, the RL algorithm can try different actions, and observe the well-defined consequences in the safety of a docker container.
But what about messy real-world situations involving people? The rewards are unclear, the stakes are high, and you can’t experiment in the real world. But these situations are precisely where the next big opportunity in AI is. To crack this, we need to *simulate* society (“put society into a docker container”). Concretely, this means building a model that can predict what will happen in any given situation (real or hypothetical). If we can do this, we are only limited by our imagination: predict the future, optimize for better outcomes, answer hypothetical (“what if”) questions. Ultimately, this goes beyond making better decisions, but it’s about giving us a better understanding of ourselves and the world.
Simulation is the whole enchilada. And this is exactly the research that @simile_ai is working on. Read more here:
Show more
Simulating humans is such an interesting and useful problem but very comps, if anyone can do it it’s this team @joon_s_pk @percyliang @msbernst
Our work on generative agents showed that it's possible to accurately simulate human behavior by capturing rich information about real people.
@joon_s_pk spoke with @Nature about how our work builds on this research, and how enterprises can now use simulations to test decisions before they hit the real world:
Show more
Exciting to see @WSJ cover what we’re building at
@simile_ai.
It’s great to see the technology we developed in the lab making real world impact alongside foundational institutions like CVS and Gallup. Nothing like frontier research meeting real PMF!
Show more
Simile is increasing decision-making capacity and decreasing research time. We are proud to work with partners like @CVSHealth! 🤝
Projects that took months are now taking hours, and studies are closer resembling human behavior than prior self-reported research - all with the goal of providing the best products and services for customers at companies like CVS Health, where the customer is centered in every decision.
Read more in the CVS Health whitepaper below.
Show more
Fun to see this. We can achieve agentic behaviors with simpler prompts using today's models. Below are mine when I built Smallville in 2023 with GPT-4 base.
Here is my system prompt for the NPCs. Working pretty ok. Good variety. Feel free to crib.
I still remember the excitement in 2023 when Stanford Smallville was launched. It was the largest multi-agent sim back then - yes, 25 bots felt like a lot. Today it's the "Bigville" moment. We are seeing a nascent, massive-scale alien civilization sim unfolding in real time: orders of magnitude more agents, way higher IQ, in-the-wild access to the internet, backed by the full arsenal of MCPs.
What can possibly go wrong?
Show more
