Testing Kimi K3's 32-Page Chain of Thought
emollick · x · 2026-07-19
While testing **Kimi K3**, Ethan Mollick asked it to pick two poems that best reflect the "current state of GenAI models." Two notable takeaways from the results: - The chain of thought (CoT) spanned a massive **32 pages**, and the content itself was "quite interesting." - However, it also exhibited many **loops and dead ends**, which is one of K3's typical behaviors. In the attached image, the author compares several candidate poems one by one, discussing which imagery best maps to LLMs—such as "mirrors," "fables," "automata," and "combinatorial rearrangements"—focusing on finding poetic facets that reflect model behavior.
Related event: Testing Kimi K3: 32-Page CoT Loops and English-Dominant Reasoning(5 posts)→
More from Models
- Kimi K3 tested against Claude Code in the same Pi harness workflow — tomcrawshaw01 · 2026-07-21
- OpenAI and Anthropic complaining about Chinese open-weight models is “absurd,” says poster — krishnan · 2026-07-21
- Anthropic researcher says Fable5 proved a Jacobian counterexample after 87 years — 歸藏的AI工具箱 · 2026-07-21
- PrismML’s Bonsai 27B reportedly fits in 3.8GB and can run on a phone — tony10000 · 2026-07-21
- actAVA AI launches Cura, a 1T-parameter healthcare agent model — _akhaliq · 2026-07-21
- Users say Claude Fable has picked up a more rigid Gemini-like habit — teortaxesTex · 2026-07-21