✳flâneur — a map of the web's best reading
Large Language Models can Simulate Everything | Kevin Liu
kliu.io · 1,378 words · saved by 1 readers
And they should.
And they should. TL; DR: Simulation is the only way to forecast how future complex / AI systems will misbehave. This is post #1 in a series of 3 outlining my current views on AI. Part 1 focuses on the need for improving how people think , rather than improving their leverage over the world. Part 2 gives “no brainer,” objective strategies helpful for improving the safety of ML systems on the margin. Part 3 focuses on the best ways to measure and empirically evaluate ML systems as they are deployed in the world. A hot take: the #2 most important use case for AI in the next decade will be perform
Explore this link on the map →related reading
- AI 2027ai-2027.com
- Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
- Simulators — LessWronglesswrong.com
- AI in 2025: gestalt — LessWronglesswrong.com
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- How fast is AI improving? - AI Digesttheaidigest.org
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- AI 2027ai-2027.com
- Predicting model behavior before release by simulating deployment | OpenAIopenai.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com