Hacker News

Favorites Setup
☰
Comment by unleaded | original | ZCode – Harness for GLM-5.2
[−]unleaded · 2026-07-01 Wed 20:01 UTC · link
As someone who doesnt use these tools, why does every AI company need their own version of Claude Code? Is there more to it than vendor lock-in?
[−]theredleft · 2026-07-01 Wed 20:02 UTC · link
implementing their own version of steganographic monitoring lol
[−]dcre · 2026-07-01 Wed 20:17 UTC · link
A joke but also not a joke.
[−]ambicapter · 2026-07-01 Wed 20:19 UTC · link
"Quality" of the harness matters a lot to the user experience, and the construction of the harness will depend on the behavior/quirks of the underlying model. So, if you're using Claude Code, you can expect it to work best with Anthropic models, and expect other model-makers to want you to use the harness they've developed.

But mostly vendor lock-in, I imagine.

[−]computerex · 2026-07-02 Thu 02:48 UTC · link
Why not? They are relatively easy to make so why not. Even I made one: https://github.com/computerex/z
[−]cheesecakegood · 2026-07-02 Thu 03:18 UTC · link
There are different grades of vendor lock-in. There's mechanical lock-in (which is a thing, like .claude folders) and economic lock-in but then we don't pay enough attention to behavioral lock-in. Habit is powerful, and if you can habituate users into a certain flow, change feels bad and they are more likely to stay.