Airfoil(ciechanow.ski)
2422 points by todsacerdoti | 280 comments
Bartosz Ciechanowski's interactive article explaining how airplanes fly by examining the forces generated by airflow around wings and airfoils.
First screen, captured .
Looks similar
Airfoil(ciechanow.ski)
4 points by gronky_ | 0 comments
Moon(ciechanow.ski)
2976 points by todsacerdoti | 248 comments
Bartosz Ciechanowski's interactive article explaining the Moon, its phases, and its orbital path around Earth.
Moon (2024)(ciechanow.ski)
245 points by simonebrunozzi | 38 comments
Gears (2020)(ciechanow.ski)
124 points by mhb | 5 comments
GPS – Bartosz Ciechanowski (2022)(ciechanow.ski)
11 points by srathi | 1 comments
Related stories
Generative Agents: Interactive Simulacra of Human Behavior(arxiv.org)
326 points by mmq | 178 comments
arXiv paper introducing generative agents, LLM-powered software agents that simulate believable human behavior in an interactive sandbox environment.
Understanding Reasoning LLMs(magazine.sebastianraschka.com)
442 points by sebg | 163 comments
Sebastian Raschka's Ahead of AI newsletter article explaining the four main approaches to building and refining reasoning LLMs.
Native apps written in TypeScript and CSS(github.com)
108 points by arbayi | 37 comments
GitHub repository of example Gea applications and tools, including an app gallery for the simulator, embedded targets, GeaOS and Apple targets.
The Chalk and the Airplane(unintendedconsequenc.es)
23 points by paulorlando | 9 comments
Blog essay on mathematicians' emotional reactions to AI-generated proofs, framing it as the end of math's romantic era and comparing it to past industrial disruptions.
SkillsBench: Benchmarking how well agent skills work across diverse tasks(arxiv.org)
333 points by mustaphah | 142 comments
arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.
Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)
561 points by Anon84 | 136 comments
UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.