It's really remarkable how dramatically the way I work has changed in just a few short months. The parts of my job in front of a computer are almost unrecognizable vs. before. I'm lucky that it clicks so well for me, but I can completely understand why so many engineers are deeply disconcerted.
I love this Claude skill, by
@grimalkina :
https://github.com/DrCatHicks/learning-opportunities. It's a really fantastic start at turning LLM-assisted coding from something folks fear will sap their skills into a great opportunity for clear-headed learning and continuing education. And instead of making those separate activities, why not both at once? Try it out!
GitHub - DrCatHicks/learning-opportunities: A Claude Code skill for deliberate skill development during AI-assisted coding
A Claude Code skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
@mikeash It's also an open question in my mind how much the sphere of things-you-don't-need-to-review grows over time. My window of prediction for how autonomously-good this will get in the foreseeable future has shifted substantially towards "very", albeit still with a wide band of uncertainty.
@mikeash I think it depends on what you're doing. I carefully review my production code (and I'm professionally required to!) And I still do a lot of opinionated iteration even with AI-first workflows. But I've also written some "I haven't reviewed the code, and I don't care to" tools for personal use. With the right scaffolding, workflows, and validation, code review can be a waste of time for certain things. Having a solid conceptual grounding + planning up front makes a huge difference.
*Good* AI review is key, though. Just asking a model to review my code is pretty hit-or-miss. But using a high-quality Claude code skill for structured review does a lot better. & cross-model review seems to do even better (esp w/ a well-structured prompt/skill). E.g. Opus + Gemini, or Codex + Opus.
For all the talk about AI coding slop, the right workflows can go the other way. I pride myself on writing meticulous code & building deep understanding, and can change fragile code without regressions; but running my commits through a good AI review often still catches things I would have missed.
Rick Ballard
@rballard.bsky.social
· 2m
Relatedly, I am super proud of my colleagues who built a best-in-class in-IDE agentic programming experience for Xcode. It's a pleasure to use, and it works super well!
https://developer.apple.com/videos/play/tech-talks/111428
Meet agentic coding in Xcode - Tech Talks - Videos - Apple Developer
Discover how Xcode 26.3 seamlessly integrates coding agents like OpenAI Codex and Claude Agent to work together on complex, multi-step...
It's clear how nascent the tools are; how much dramatic improvement we'll get just from better context engineering, tooling, orchestration, and validation. It's a time of rapid experimentation, & moving at a crazy pace. The past couple months especially have felt like gaining software superpowers.
I haven't been posting about AI because people get dogpiled for it. And it is a societally complicated topic. But: I have been having more fun lately than at any point in my career. (And I've had a fun career 😄). Agentic programming has gotten *really* good. Especially with a thoughtful operator.
Interested in improving Xcode? My team is hiring!! note that this position is located in Vancouver, BC 🇨🇦🌲
#Xcode #FediHire #Applehttps://jobs.apple.com/en-us/details/200641971-3350/xcode-performance-engineer
Xcode Performance Engineer - Jobs - Careers at Apple
Apply for a Xcode Performance Engineer job at Apple. Read about the role and find out if it’s right for you.
ana