How to replace a large, expensive, and slow model with a small, cheaper, fast model and…
This is a vibe coding post classified by AGK Intelligence as Skills & agent setups (a workflow), kept by the Vibe Coding Radar because it carries real work, not commentary.
How to replace a large, expensive, and slow model with a small, cheaper, fast model and still get the same results. 7x faster and 50% fewer tokens. This is like fine-tuning, but without touching the model. Here, we teach Haiku, using Zep Agent Skills, to do what Opus 5.5 does to complete a task. • It takes 7 minutes with Opus 5.5. Only 59 seconds with Haiku. • It takes 1.4M tokens with Opus 5.5. Only 700K with Haiku.
Posted by Santiago (457.4k followers) 21 h ago · 137 likes · 13.6k views · view the original post on X. Kept by the Vibe Coding Radar as Skills & agent setups.
More vibe coding work like this
- Here are 10 new AI agent skills for Claude Code, Codex and more — @shushant_l
- 做产品演示视频，录完屏还得手动加缩放、调鼠标、配字幕，一条一分钟的视频能剪一晚上。 — @GitHub_Daily
- Your AI agent can now build with MagicBlock — @magicblock
- this is f*cking unreal, one site taught me agents better than any $2000 course — @Sprytixl
- I'm gonna uninstall Blender tonight. A dev just dropped a free Claude skill that turns… — @elvar_official
- most people skip redirect mapping — @webjuice_ie
- 写项目文档要配一张架构图，光去各家官网找 Logo、对齐连线就得折腾一下午，画完箭头还压着字。 — @GitHub_Daily
- GitHub真的是AI时代最好的脚手架！！！ — @yyyole
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:18 UTC. Full method.