When Gemini 3 came out I said it's the greatest model of all time. I loved it. But it didn't work for others.
This week I'm seriously trying GPT-5.2 and already said it might be better than G3.
Today, GPT-5.2 let me down and I wonder...
am I...
the boy who cried GOAT?
![Screenshot of the blog post that starts with this text:
"Amp now has subagents. Here’s what they look like in action:
<screenshot of app showing subagents>
But chances are that the first sentence and even that screenshot didn’t cause your facial expression to change.
After all: who even knows what a subagent is? So let’s start there.
What’s a subagent? If you’ve read How to Build an Agent you know that we define an agent as “an LLM with access to tools, giving it the ability to modify something outside the context window.”
Subagents are tools, too. They are agents that can be started by the main agent, the one you’re interacting with when you use Amp.
[...]"](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:mqqgy3lhxf37sp5nx2zc23mn/bafkreideiejxotc4g4cebcha2l257zyj3ahpnrdueaggblc32j7kiek5qm)
