3/ Recaps We shipped recaps earlier this week, to prep for Opus 4.7. Recaps are short summaries for what an agent did & what's next. Very useful when returning to a long-running session after a few minutes or a few hours.
@bcherny
-
AI Model Focus Mode Enables Autonomous Command Execution
By
–
4/ Focus mode I've been loving the new focus mode in the CLI, which hides all the intermediate work to just focus on the final result. The model has reached a point where I generally trust it to run the right commands and make the right edits. I just look at the final result.
-
Maximizing Productivity with Opus 4.7: Practical Tips
By
–
Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7
-
Opus 4.7 Auto Mode Enables Autonomous Complex Task Execution
By
–
1/ Auto mode = no more permission prompts Opus 4.7 loves doing complex, long-running tasks like deep research, refactoring code, building complex features, iterating until it hits a performance benchmark. In the past, you either had to babysit the model while it did these sorts
-
New AI Skill Reduces Permission Prompts in Development
By
–
2/ The new /fewer-permission-prompts skill We've also released a new /fewer-permission-prompts skill. It scans through your session history to find common bash and MCP commands that are safe but caused repeated permission prompts. It then recommends a list of commands to add to
-
AWS Bedrock model provisioning requirements and setup
By
–
Do you have the model provisioned for your Bedrock account?
-
Anthropic increases rate limits for Opus 4.7 subscribers
By
–
Opus 4.7 uses more thinking tokens, so we've increased rate limits for all subscribers to make up for it. Enjoy!
-
Rate Limits Increased for All AI Subscribers
By
–
We've raised rate limits for all subscribers to make up for the increased token usage. Enjoy!
-
MRCR Evaluation Method Replaced by GraphWalks Approach
By
–
MRCR is a bad eval, we use GraphWalks now. More info here:
-
MRCR Evaluation Method Replaced by GraphWalks Approach
By
–
MRCR is a bad eval, we use GraphWalks now. More info here: