We just published internal data on how much of Claude's development is already being done by Claude:
- Over 80% of all code merged into our codebase is now written by Claude
- It's been months since many researchers at Anthropic hand-wrote code
- The typical Anthropic engineer ships 8x as much code as they did in 2024
- On the most open-ended engineering tasks, Claude's success rate jumped from ~26% to 76% in 6 months
- When research sessions went off-track, Claude proposed a better next step than the human took 64% of the time
We're not at recursive self-improvement yet, but it could come sooner than most expect. I highly recommend reading the full blog post.
We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal.
Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell.
The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.
Small new in the Claude API: set max_tokens on the advisor tool to cap its output. Predictable cost and latency for agents that consult an advisor every step, and stop_reason: "max_tokens" tells you when the cap was hit so your agent can adapt.
https://t.co/jZC9VP7VYj
there's a ton of demand right now for excellent infra talent, definitely outpacing supply
im hiring engineers who have tackled megascale, multicloud product infra to work on the Claude Platform. help me find them 🙂
We’ve updated Claude Code's built-in claude-api skill migration guidance for 4.8.
Run "/claude-api migrate" to update your model strings and suggest prompt improvements that are tuned for Opus 4.8.
Opus 4.8 is out: better judgment, catches its own mistakes.
My favorite API addition: mid-conversation system messages. Append {"role":"system","content":"new rules"} mid-task. Instructions update without breaking the prompt cache, and reminders keep long runs on track.
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.
today, the @StainlessAPI team is joining @AnthropicAI !
we're bringing together experts in SDKs, CLIs, and MCP servers with the creators of MCP to make agents built on the Claude Platform even more connected & powerful.
https://t.co/LXl20Ly72y
The Claude Platform on AWS is now generally available.
AWS customers get the full set of Claude API features, with AWS authentication, billing, and commitment retirement.
My @ClaudeDevs Code with Claude talk is up: Getting more out of the Claude Platform. I built an agent for superheroes — turns out the real villain was the token bill. Caching, context management, and the Advisor took it down. 🦸
https://t.co/YOrO3fNqbS
Had a blast on stage at Code with Claude with @mariorod1 — how @github ships Claude to millions of devs across Copilot and pushes quality up + cost down: caching, harnesses, and the new Advisor pattern. Thanks Mario 🙏 @ClaudeDevs
https://t.co/oi9tCsYKDA
come say hi at Code With Claude tomorrow!
ill be giving a talk w @jess__yan on some new things we’re excited to share.
join the livestream here:
https://t.co/9V8GNWwdIk
I get double duty at Code with Claude SF tomorrow 🦸
Claude Platform talk - the demo has super powers, that's all I'm saying :-)
And I am on stage with @mariorod1 from @github for something we've been cooking together
Free livestream: https://t.co/o7ysFquaWT
Managing API keys is one of the top security concerns we hear from customers.
Today we’re introducing keyless auth for Claude Platform: authenticate via browser with the CLI, or let workloads use their existing cloud identity (AWS, GCP, Azure, or any OIDC token provider).
Production-ready Claude API code, wherever you build.
The claude-api skill now ships in @coderabbitai, @jetbrains, @resolveai, @warpdotdev and Claude Code - fewer errors, better caching, cleaner agent patterns, smoother model migrations.
https://t.co/sPXC8qG1pk
i really like the new prompt caching dashboard in Claude Console. prompt caching is impt for saving cost + improving latency. this dashboard provides very useful diagnostics + visibility.
recently i asked an @AnthropicAI PM @brada if he'd buy land in Bariloche to survive post-AGI
he laughed. said he's been kissed more times in Argentina than anywhere else and that's his new plan.
Argentina been blowing up with cool events lately.