Kimi K3 behaves very differently across API, Claude Code, and its native client
APPSO · wechat · 2026-07-23
This hands-on comparison tests Kimi K3 in four setups for a screenshot-to-HTML task: direct API, Claude Code, Kimi’s native client, and Codex.
What happened
- Direct API: shortest path, but no process feedback; despite that, it delivered the first runnable page fastest.
- Claude Code: felt like a real coding agent because it could inspect files, use the terminal, and iterate, but the first pass generated code without actually writing files to disk.
- Native Kimi client: showed the model inside Moonshot’s own prompting, tools, and delivery flow.
- Codex baseline: used as a comparison point after the bridge to Kimi through CCSwitch kept failing with 502 errors.
Main takeaways
- The same model can behave very differently depending on the harness around it.
- Agent wrappers can add capabilities, but they also add new failure modes: file writes, tool calls, execution feedback, and verification can all break.
- The native client is valuable not because it always produces the prettiest output, but because it hides the operational complexity from normal users.
The article’s bigger point: “wrapper” is not just packaging. A harness can organize capability, create capability, and introduce new bugs at the same time.
More from coding & agent
- An AI agent made the code 10× faster, but the results were terrible — francoisfleuret · 2026-07-23
- A builder’s playbook for products designed for both humans and AI agents — slobodan_ · 2026-07-23
- An AI memory system combines AGE, pgvector and relational tables with emotional decay — QuixiAI · 2026-07-23
- HiSME lets LLM agents evolve the way they evolve skills, without changing weights — 机器之心 · 2026-07-23
- Hexis shifts agent design from assistants to long-term memory and identity — QuixiAI · 2026-07-23
- Abacus AI pitches an all-in-one agent stack for websites, apps, ads and support — bindureddy · 2026-07-23