This is GLM 5.2 creating and describing *images*
How, since the model is text-only?
With Amp's specialized subagents.
Multi-modal agentic workflows at the pareto frontier of intelligence, speed, and cost.
GLM 5.2 in Amp. Zero data retention, US and West-based inference. It's a good model.
Try it now:
amp update
amp plugins add --auto-update @amp/glm-52-mode
amp --mode glm-5.2
Understanding the code is now a key bottleneck in agentic coding.
Amp now shows you the diff for any thread and lets you stage and provide feedback on changes.
Just shipped some "how did we not have these yet"s in Amp:
• Customizable keybindings (see `amp config keymap` and ampcode.com/manual#cli-key…)
• Mode switcher that tells you about each mode (Ctrl+S in the Amp CLI to use it)
Watch me use these in Amp to fix a bug:
Amp's deep & rush modes (GPT-5.5) now finish your work up to 40% faster.
We rebuilt Amp last month to make this possible, cutting hops between you⭤GPU and running agent loops in durable execution to get the max benefit from long-lived OpenAI websockets.
ampcode.com/news/faster-de…
I love when technological progress kills a feature.
The models are so good that (A) this feature is too risky and (B) it's not needed anymore to convince people that agents are good.
ampcode.com/news/end-of-pu…
