aiqbench takeAI Products
aiqbench analysis
This piece documents an experiment using the latest Claude model (Opus 5.5) to generate a functional Three.js web game via natural language prompting, highlighting the model's ability to orchestrate complex creative assets like music and animation over several hours of inference time. The core focus is on the practical application of large language models for rapid prototyping and generating interactive media, rather than discussing underlying quantum mechanics or general consumer tech trends.
3
Sources coveringSimon Willison, LessWrong, Latent Space
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.
Tree Appreciator
Simon Willison1 min read

Another game experiment with Claude. This one used the default Claude iPhone app (chat mode,…
Excerpt shown under the publisher's RSS terms · 15 words · full text and figures are on the publisher's site
Related coverage

AI & Society
Presentation: Getting Rid of LeetCode Interviews in the World of AI
InfoQ · Jul 29, 2026

AI Safety
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Latent Space · Oct 16, 2026
AI Safety
Problems of Proliferation
LessWrong · Sep 29, 2026

AI Research
Social Theory and Agent Foundations
LessWrong · Oct 8, 2026