Unrelated but I have a similar problem with speech to text apps on windows, where due to the funkiness of claude codes (necessary) implementation, it doesn't send the keybindings correctly.
sooooooooooooooon! nobody on the team daily drives windows yet so until we have an engineer on the team driving windows we probably wont be able to properly support it.
Clever Benefits | Scottsdale, AZ (Hybrid — 2 days/week onsite, North Scottsdale) | Full-time | $140k–$180k | Senior Full Stack (React/React Native/Node/AWS)
Clever Benefits is hiring a Senior Full Stack Software Engineer to help build and scale our platform. You’ll ship end-to-end features across a React web app, React Native mobile app, Node.js/TypeScript backend, and AWS infrastructure. Small team, high ownership, production focus.
Requirements: 8+ years experience; strong TypeScript; production React + React Native + Node; solid AWS background; Prisma/Postgres/tRPC; comfortable owning features from design → deployment. Must live within 30 miles of North Scottsdale and be able to be onsite 2 days/week.
Nice to have: TestFlight/Play Store workflows; monorepos (pnpm/bun workspaces); IaC (CDK/Terraform). Interest in using AI to accelerate development (codegen/automation) — with an emphasis on maintainable, high-quality engineering.
How to apply: Email your resume + a short note (and links/GitHub if you have them) to sal@cleverrx.com with subject “HN — Senior Full Stack Engineer”.
If I'm using cursor then sonnet is better, but in claude code Opus 4 is at least 3x better than Sonnet. As with most things these days, I think a lot of it comes down to prompting.
This is interesting. I do use Cursor with almost exclusively Sonnet and thinking mode turned on. I wonder if what Cursor does under the hood (like their indexing) somehow empowers Sonnet more. I do not have much experience with using Claude Code.