Eric Buess
@EricBuess
Trying to follow Jesus; husband/dad; AI dev/Software Eng. (MSCS)/consultant; 🎯 LEV; Anthropic Model Safety Bug Bounty; #1 fan of @AnthropicAI /Claude Code 🧙🔥
My custom extension for Cursor, Windsurf & VSCode now works with Gemini 2.0 Flash (in addition to o1, o1 Pro and Sonnet)! I might make it public at some point if I can ever figure out what to call it. Uses my web subscription so no API costs associated with calling AI models!
I'm considering publishing the solution that lets Claude Code CLI recursively call Claude Code CLI. It's different than Claude Code tasks that have been out for months or the explicit sub agents feature that was recently enabled. You can already manually kick off Claude Code CLI…
More about Claude Code sub agents! What works. What doesn't. Powerful patterns. And what I've found solutions for that will unlock even more agentic potential with a little effort. Sub agents + hooks + context sharing + sub agents spawning full Claude Code CLI instances... 🤯…
Your connected tools are now available in Claude on your mobile device. Now you can access projects, create new docs, and complete work while on the go.
I'm making a list of all the non-coding things people are doing with Claude Code. What are you using Claude Code for?
Answers to my initial questions about Claude Code sub-agents! It's great having the Claude Code docs searchable locally ... github.com/ericbuess/clau…
So happy about this! I'll dig in over the next few days! Very interested in the best ways to intelligently share context and where the context sharing mechanisms can be improved. That feels like one of the most important aspects to get right. Could be an MCP layer or separate…
Subagents let you create teams of custom agents, each designed to handle specialized tasks. Examples of subagents we’ve seen be useful are: Software Architect: help design features elegantly and ensure appropriate layers of abstraction Code reviewer: Review best practices in a…
Get started with subagents today with the /agents command, and read the docs to learn more: docs.anthropic.com/en/docs/claude…
We are still accelerating. Sub-agents are now a first-class feature in Claude Code. I can't wait to see what you build with them. Great work on this @sidbidasaria
Claude Code is getting a brand new feature: custom subagents. Type `/agents` to get started.
Turn written content into professional designs with Claude + @canva Upload any document — blog post, product guide, meeting notes — and ask Claude to turn it into branded visuals
Yes! Thank you @AnthropicAI!
We've increased Tier 1-4 rate limits for Claude Opus 4 on the Anthropic API: Tier 1: 20K → 30K ITPM, 8K OTPM Tier 2: 40K → 450K ITPM, 90K OTPM Tier 3: 80K → 800K ITPM, 160K OTPM Tier 4: 200K → 2M ITPM, 400K OTPM
We're launching an "AI psychiatry" team as part of interpretability efforts at Anthropic! We'll be researching phenomena like model personas, motivations, and situational awareness, and how they lead to spooky/unhinged behaviors. We're hiring - join us! job-boards.greenhouse.io/anthropic/jobs…
I was using Claude Code wrong... Here’s what I learnt and how I maximise Claude Code performance + Best tips that ACTUALLY useful 👇 Thread below
The White House AI Action Plan gets it right on infrastructure, federal adoption, and safety coordination. It reflects many policy aims core to Anthropic.