AI - AI Dynamics

→ View original post on X — @simonw

21GB AI Model Runs on 32GB Hardware Machine

By

@simonw

–

16 April 2026 20h38

128GB M5, but this 21GB model should run OK on a 32GB machine

→ View original post on X — @scobleizer

Smart Technology Investment Opportunity Met

By

@scobleizer

–

16 April 2026 20h38

Yeah, I had the same feeling when I met him. I wish I had capital to invest in these things, but very smart.

Configure Opus 4.7 Effort Level for Adaptive Thinking

By

–

16 April 2026 20h38

5/ Configure your effort level

Opus 4.7 uses adaptive thinking instead of thinking budgets. To tune the model to think more/less, we recommend tuning effort.

Use lower effort for faster responses and lower token usage. Use higher effort for the most intelligence and capability.… pic.twitter.com/h2gY3yQEeK
— Boris Cherny (@bcherny) 16 avril 2026

5/ Configure your effort level Opus 4.7 uses adaptive thinking instead of thinking budgets. To tune the model to think more/less, we recommend tuning effort. Use lower effort for faster responses and lower token usage. Use higher effort for the most intelligence and capability.

Verify Claude’s Work to Maximize AI Output

By

–

16 April 2026 20h38

6/ Give Claude a way to verify its work Finally, make sure Claude has a way to verify its work. This has always been a way to 2-3x what you get out of Claude, and with 4.7 it's more important than ever. Verification looks different depending on the task. For backend work, make

Claude Opus 4.7 Enhancement Enables Longer Agentic AI Workflows

By

–

16 April 2026 20h38

Happy coding! Opus 4.7 is a significant step up. To get the most out of it, take the time to adjust your workflow to take advantage of Claude running for longer & being more agentic. It feels like a nice improvement with old workflows, and a significant leap once you take the

Recaps Feature Ships for Agent Session Continuity

By

–

16 April 2026 20h38

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.

AI Model Focus Mode Enables Autonomous Command Execution

By

–

16 April 2026 20h38

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.