New on our Engineering blog: Creating in-house source control.
In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.
Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: https://t.co/wzNkwHs7IN
Just to avoid some confusion: auto-compact does summarize. When it runs, your whole conversation is replaced by a short summary. It doesn't keep the last 1M tokens around.
The ~967K is only when it runs on 1M models. Compacting itself is just one request that reads about as many tokens as the message you sent right before it, and it's mostly cache reads if your cache is still warm.
What @rohit3a found is that waiting until 967K means every message before that point uses a lot of tokens, because each one includes your whole conversation so far. Most of it is read from the cache, which is much cheaper (so this is usually fine as long as your cache is warm), but it still counts toward your usage and adds up as your conversation grows.
/autocompact 400k makes it summarize at 400K instead, so your messages never get that big.
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.
It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
💻Introducing Googlebook OS, our new platform that combines the best of Android and ChromeOS!
Googlebook OS is built on the Android tech stack and is paired with desktop foundations from ChromeOS, and it'll get updates for up to 10 years!
Learn more👇
https://t.co/tNA5sXjNHD
project.pbxproj is dead 🪦
Xcode 27.2 ships a JSON project format (.xcproj): default for new projects, readable, merge-friendly, agent-editable.
https://t.co/6mw74v8C6w
Today, we are announcing a partnership with @mozilla to bring privacy, control and choice to people using AI to browse online. 🦊🐈
https://t.co/Bsd6N4jNdV
Omacom Foundation just keeps committing to sponsorships! We're onto our third, this time for @jdxcode and mise with a premier sponsorship. Just in time to pay for our traffic surge 😂 https://t.co/bs0v0a3PC2
usage-rs (my blazing fast rust cli framework) is ready for testing! ~2500x faster than clap!
It’s mostly clap-compatible, but uses a serde-like architecture: your CLI is compiled into a static command map instead of rebuilding a command tree every time the program starts.
- config-file and env var integration
- negatable flags (--color/--no-color)
- expression based validation
- resolves clap's most upvoted issues
- smaller binary size: 1.5mb (usage-rs) vs 3.1mb (clap)
- NO THIRD PARTY CRATES! (except proc-macro2)
- includes advanced completion and docs generation like my clis all have (usage-cli is not required for end users anymore!)
it's experimental so there may be breaking changes in point releases for now. If you try it out, I'd love it if you could have your agent send me a summary of how well or not so well it went as a gh discussion.
https://t.co/OTCCGh6UoE
@levelsio@lulumeservey Everyone overthinks marketing.
For every product launch we did at X, I wrote the announcement 20min before clicking post.
Better to be launching something every week instead of focusing on how to make a single-day traffic spike slightly larger.