Notes on "Amp"

Here’s what I missed in the AI field this week — I was on holiday in Tokyo.

Two new models dropped within about 15 minutes of each other: Claude Opus 4.6 and GPT-5.3-Codex. Amp immediately adopted Opus 4.6 for its smart mode, but GPT-5.3-Codex is only available in their Codex app, not yet via the API. I believe Amp will adopt it for its deep mode once it’s generally available.

Amp is sunsetting the editor extension next month. It hasn’t been officially announced yet, but the team mentioned it in their latest Raising An Agent podcast episode. I use Amp exclusively through the editor extension, so unfortunately I’ll have to switch to the TUI version and get used to it.

Ghostty’s author Mitchell Hashimoto has been busy lately:

• Ghostty’s updated AI usage policy for contributions. More and more open source projects are drowning in AI-generated issues and PRs submitted without human review — the slop. He proposed a new policy for dealing with this trend. It’s not against AI, but makes every AI-generated contribution accountable to a human.
• Vouch, a community trust management system. A tool that puts the policy above into practice. To mitigate the slop burden, open source projects should build a network to identify trustworthy contributors.
• My AI Adoption Journey. Mitchell’s reflections on his AI adoption journey. Most of it resonates with me — and probably with every thoughtful developer.

Diffs (via). Amp is planning to support code diffs for threads, built on this library. Its functionality, demo, and docs are all neat. Bookmarking it here so if I ever need to build code diff functionality, I’ll have it handy.

I now use ChatGPT and Amp in a very simple way: I just create new threads and leave them as-is.

Previously for ChatGPT, I created several projects, and when I wanted to talk to it, I’d find and continue a relevant existing thread or create a new one in a project. I’d organize them periodically. Turns out it just looked neat but didn’t actually help. Now I just start a new chat when I think I need to. ChatGPT memorizes context automatically, which is sufficient.

Similarly for Amp, I used to organize my threads very carefully. After the labels feature shipped¹, I started to label every thread manually after I completed one. I finally realized this practice doesn’t help — for now. So I deleted all the labels. And when to make a thread public? When I find I need to.

When you start using a tool, use it with the least friction and in the most intuitive way. Any feature that forces redundant manual work isn’t worth the hassle. Only use a feature if you find you need to.