Claude by Anthropic
A family of foundational AI models
5.0•693 reviews•43K followers
A family of foundational AI models
5.0•693 reviews•43K followers
We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale.
This is the 33rd launch from Claude by Anthropic. View more
Auto Mode by Claude Code
Launching today
Claude Code’s new auto mode lets Claude approve file writes and bash commands for you. A classifier checks each action: safe ones run automatically, risky ones get blocked and handled differently. Use in isolated environments.
Free
Launch Team
Claude’s latest “Аuto Мode” might be the smartest update yet by @Claude by Anthropic.
It bridges the gap between AI thinking and action by letting Claude handle file writes, commands, and workflows on your computer. With permission and without constant approvals. Safe actions run automatically, risky ones get blocked and handled differently.
Set it once, let Claude manage repetitive tasks, scripts, or reports, and free your attention for higher-level work. Perfect for devs, operators, and founders who want AI to actually do, not just suggest.
Available on Team plan now; Enterprise and API coming soon.
BrandingStudio.ai
Umair is right on, the 90% rubber stamping was never the real friction, it was just the visible friction. The actual problem is the 10% where you need to understand what Claude is trying to do and why before you can make a good call. If the classifier just blocks those with a generic message and no context, you've traded one interruption for a worse one.
What I'd want from auto mode is not just safe/blocked but a third state: "proceeding but flagging this for your review." Something that lets the session continue without stopping but surfaces the decision for you to audit after. That way you're not context-switching mid-flow but you're also not flying completely blind on the edge cases.
Use Claude Code daily and the constant approvals do break the flow, especially on long agentic sessions. The right trust model here isn't yes/no per action, it's more like a pilot and autopilot relationship. Autopilot handles the cruise, the pilot takes over when conditions get genuinely tricky. Curious how the classifier is trained and whether it improves over time on the user's specific codebase patterns.
the classifier is doing the same thing i already do mentally when i hit yes/no on approvals. 90% of the time its obviously safe and im just rubber stamping it. nice that they automated the rubber stamp but the real problem was never the safe actions, its the 10% where claude wants to do something genuinely weird and you need context to judge it. curious if the classifier catches those or just lets them through with a generic "blocked" message
Triforce Todos
This sounds amazing, finally an AI that actually does things instead of just talking about them