VideoPrompt Engineering · Oct 25, 2026
Kimi K3.1 Pro and Opus 5.5 Made the Same 13 Apps (Raw Results)
Kimi K3.1 Pro vs Claude Opus 5.5 on 13 long-horizon agentic coding tasks. Both models ran in the same Claude Code harness, with the same prompts, the same effort setting and the same grading scripts.
More to watch
Prompt Engineering · Oct 26, 2026
Harness² Explained in 60 Seconds
Harness engineering
Prompt Engineering · Oct 24, 2026
Harness² Explained: Self-Improving Agents Without Training
Harness engineering
Prompt Engineering · Oct 23, 2026
Kimi K3.1 Pro: Open Weights, Almost Opus
Comparisons & reviews
Visual Studio Code · Oct 28, 2026
🍰 Compare Models & Harnesses with Agent Bake Off!
Comparisons & reviews · Evals & benchmarks
David Ondrej · Oct 28, 2026
kimi k3.1 changes everything...
Comparisons & reviews
Zero to MVP (Nick Blokhin) · Oct 27, 2026
$7 vs $0.65: Opus 5.5 and MiniMax M3.1 Flash on My Go Project
Comparisons & reviews · Cost & limits