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
@bcherny
-
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:
-
Opus 4.7 Adaptive Thinking Uses More Tokens Than 4.6
By
–
Not accurate. Adaptive thinking lets the model decide when to think, which performs better. Opus 4.7 also uses more thinking tokens on average than 4.6, which is why we have increased rate limits for all subscribers to make up for it.
-
Rate Limits Increased for All Subscribers
By
–
We've increased rate limits for all subscribers to make up for it. Happy coding!