You can now proactively verify your identity (with a passport or government ID) in case it’s needed for future frontier model access in Amp. We think it probably will be, and we want Amp to keep giving you access to the best models available to you. We can’t guarantee access criteria or timelines. Those depend on (highly uncertain) government and model lab policy. We don’t plan to impose any additional restrictions beyond what is required by law and the model labs. We are covering the cost for identity verification for all users, and we’re using Stripe for identity verification, so Amp stores nothing and sees only the outcome. ampcode.com/settings/identit…

Claude Fable 5 in Amp (via a plugin, built-in soon)

Just shipped some "how did we not have these yet"s in Amp: • Customizable keybindings (see `amp config keymap` and ampcode.com/manual#cli-keyma…) • 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-deep…

We rebuilt Amp's UI so you can watch and drive all your Amp agents on web, mobile, and CLI. ampcode.com/news/agents-ever…

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-publ…

Some of you missed thread previews. They're back, baby.

Amp Neo is now available to everyone. Time to drop the suffix. ampcode.com/news/drop-the-ne…

Proof-of-human with passkeys, for an extra layer of security when remote-controlling your Amp threads. ampcode.com/news/proof-of-hu…

Amp Labs: small teams of the best software builders, working inside the most frontier-oriented company per industry and region. ampcode.com/news/amp-labs

We're still seeing and fixing bugs and instability in the Amp Neo CLI. If you're in the Neo beta, run `amp --take-me-back` to use the non-beta Amp CLI that is unaffected by these issues. (Or keep using Neo if you want. I am.) I'm really sorry for these issues. We hit some unexpected scaling issues on this new architecture, and that's on us. We're working around the clock to get it stable and then open it up to more people. And huge thank you to everyone who's giving feedback and sending reports!

Update: not fully resolved. Rolling out changes to increase capacity.

Incident resolved. More machines for you all to run agents on. Happy hacking!

We're going through some scaling issues with our new architecture. Stand by. Until then: `amp --take-me-back` to go back to the old Amp.

The best coding agent in the world is back. ampcode.com/news/neo

Smart mode in Amp now lets you use Opus 4.6 wth 300k input tokens of context, up from 168k. Also, tokens above 200k are now charged at the same (not higher) per-token rate. Why not 1M tokens in smart? Quality/cost aren't right. If truly needed, use (hidden) large mode.

There's a new oracle in Amp: GPT-5.4. ampcode.com/news/gpt-5.4-the…

And here is the model that killed it: GPT-5.3-Codex. ampcode.com/news/gpt-5.3-cod…

We believe the coding agent is dead. Soon, Amp will look very different. ampcode.com/news/the-coding-…