I’ve much preferred OpenAI models since ~Feb But since the launch of Astra, I’ve experienced both Astra and Sol behaving in ways we haven’t seen from frontier models since Sonnet 4 circa one year ago

Epic week so far with the Amp & Amp Labs team in Sydney. @Westpac shared some of the things we have been shipping together during their investor update. 🚀 We have an update coming soon.

The most important investment in agentic coding velocity may have nothing to do with agents. Amplitude tripled its PR volume in six months. PR cycle time went from 5.2 hours to 44 minutes. Almost all of that came from fixing unglamorous infrastructure. 𝐂𝐈 𝐟𝐫𝐨𝐦 𝟑𝟎 𝐦𝐢𝐧𝐮𝐭𝐞𝐬 𝐭𝐨 𝟑: they swapped the JavaScript toolchain for native equivalents (tsc to tsgo, ESLint to oxlint, Prettier to oxfmt), moved to affected-only builds in Turborepo, and ran independent stages concurrently. Most tools got about 10x faster. 𝐅𝐮𝐥𝐥 𝐬𝐭𝐚𝐜𝐤 𝐮𝐩 𝐢𝐧 𝟐𝟖 𝐬𝐞𝐜𝐨𝐧𝐝𝐬: a custom CLI built on devbox starts every local service with one command, down from 3 minutes. 𝐕𝐚𝐥𝐢𝐝𝐚𝐭𝐢𝐨𝐧 𝐰𝐢𝐭𝐡 𝐧𝐨 𝐥𝐨𝐜𝐚𝐥 𝐬𝐞𝐭𝐮𝐩: add a label to a PR and get a frontend preview in under five minutes, or an ephemeral copy of the backend stack in the cloud. Once you have a full app stood up in 30 sec on every PR, testing and verification become much faster which decreases time to merge. 𝐑𝐞𝐯𝐢𝐞𝐰 𝐬𝐜𝐨𝐫𝐞𝐝 𝐛𝐲 𝐫𝐢𝐬𝐤: a model rates each code change on size, scope, test coverage, and API surface, and low-risk changes merge with no human. Cursor's Bugbot reviews every PR, and bug reports fell 55% even as PR volume tripled. Once CI dropped under five minutes, engineers stopped working locally. Remote is the new dev environment.

Ok here's another one. @AmpCode orbs can spawn other orbs (h/t @thorstenball for the cool demos) so I can create a main orb to design the feature and then it coordinates and oversees the implementation. In this case the main orb is in Ultra mode and all the worker orbs are medium mode. Then main orb reviews what the workers did, makes edits (or requests them) and commits the changes. You can steer the work as it happens but you don't have to create all the new "chats" by hand. It's all handled by the main agent. In some cases it spawned parallel orbs for separate concerns, then reconciled everything and kept pushing. And for this worked, it paused every time it had a shippable slice, showed proof of work (screenshots of the feature being used in the dashboard app), asked for clarification or confirmation on some of its decisions. And this (kinda complex) feature is now production ready in a few hours, half of it dictated from my phone in between house chores, taking out the dog or putting my daughter to bed last night. Orbs are awesome

25 years ago, america mourned together. a long, confusing process. but we were a country. if it happened today the streamers would be blaming trump and the jews by this afternoon, and leftoids on tiktok would be saying the bankers deserved it. we’ve lost more than we realize.

I recorded how I use agents day to day. In this video: • Agents spawn other agents to check whether performance improvements actually helped in production. • I have an agent fix UI flicker and test the result in a portal. • We investigate and fix an `amp clone` bug for a Nix user. • I toggle feature flags directly from the remote machine. • I ask an agent for "irrefutable proof" that its fix works. You can see all the prompts, what the agents do, and how I review their work (or don't). Timestamps: 0:15 Shipping and monitoring performance improvements 2:11 Investigating an amp clone bug in Nix 3:51 Fixing UI flicker and testing in a portal 5:55 Starting an agent to promote Recap to an opt-in experimental feature 7:45 Previewing the sidebar flicker fix in a portal 9:38 Reviewing production performance canaries 11:45 Checking in on the production fix and granting read-only log access 12:47 Check Recap Experimental Setting Copy 13:39 Check in on amp clone Nix fix 14:49 Sidebar fix deployment check schedule 15:35 Checking in on performance fix thread's log analysis 16:14 Asking the agent for irrefutable proof of its fix 17:00 Checking Recap experimental setting 18:31 Testing a mechanical refactor of the CLI 21:48 Checking amp clone nix fix agent evidence 23:20 Checking feedback from Slack

Make Amp's dial your own. Choose the models behind the builtin modes. Use your API keys or ChatGPT subscription for supported models. Or add your own custom mode.

Interesting. Gurman reporting that Cook will earn ~$45m next year as Executive Chairman. Gurman compares it to Bob Iger’s comp after moving to the same role at Disney, which famously resulted in Iger canning his hand-picked successor and returning as CEO.

When @thorstenball tells you that orbs aren't just "cloud agents", you should listen. @AmpCode makes it _so easy_ to coordinate large chunks of work through properly sized agents (both in terms of intelligence and compute). Built-in message-passing pays off!