I've been using GLM-5.2 extensively over the past few days, primarily for software engineering tasks through OpenCode and Hermes-Agent, and it has genuinely impressed me.
The biggest compliment I can give is that, during many coding sessions, it gave me a similar feeling to using Claude Opus. Not because the models are identical, but because of how reliably it understands context, follows complex instructions, and completes multi-step engineering tasks.
I also tested it through Ollama Cloud using an API key, and the experience was consistently solid across different environments.
What I appreciate most is that the team decided to open-source such a capable model. The AI community benefits enormously when high-quality foundation models are openly available, and I wanted to leave a review simply to thank and recognize the work that went into this release.
Looking forward to seeing how the project evolves.
Flowtica Scribe
Hi everyone!
AutoClaw is built for the kind of work that starts as one message and somehow ends up touching a spreadsheet, a browser, a few files, and several apps.
Give it the goal in AutoClaw or message it through IM, and it can break the task down, operate the tools it needs, keep longer jobs moving, and send the result back into the conversation.
That works nicely for things like recurring ops, research, content work, or the random business task that never fits neatly inside one app.
GLM-5.3 is now available natively too, and you can connect an existing GLM Coding Plan directly.
New users also get 26K credits to try it out!