The rise of agentic AI tools is opening up an opportunity to bring us back to that original world of wonder where you could just build what you wanted, even without a CS degree.
If adopting coding agents demonstrably reduces the quality of the code and features you are producing, you should address that problem directly: figure out which aspects of your process are hurting the quality of your output and fix them.
Shipping worse code with agents is a choice. We can choose to ship code that is better instead.
In my head, some bugs belong to categories that feel important, and yet remain hard to define and quantify: embarrassing bugs, dumb bugs, flow killers.
Somewhere in the hard-to-explain space is another tricky category: UI decisions that feel cheap.
My personal (least) favorite example of a cheap UX decision is when devs (and designers) don’t take the time to accept reasonable input into forms and force the user to input the data exactly the right way. For example, when jackson@example.com (note the extra space) isn’t accepted as an email address.
Rafe Colburn, riffing on a post from Robin Sloan:
Robin Sloan describes himself as the programming equivalent of a home cook. I’ve been working in professional kitchens for a really long time, but lately I’ve rediscovered the joy of home cooking myself.
Ditto.
We’ve been talking a lot at Viget about how to customize CLAUDE.md so I’m doing some reading this afternoon:
- Learning the basics of CLAUDE.md
- Learning the basis of writing skills
- Checking out examples of skills from folks like jibbajabba, jackyliang, and obra
Simon Willison is sharing patterns (and anti-patterns) for agentic software engineering
What makes the AI chatbots and agents feel light and clean, here and now in 2026? Is it an innate architectural resistance to advertising, to attention hacks, to adversarial crud? No — it’s that they are simply new! The language models in 2026 are Google in 1999, Twitter in 2009. Their vast conjoined industry of influence hasn’t yet arisen … though it is stirring.
Missed this news last week, but Microsoft is working on a content marketplace to help content creators license access to their content to AI providers. Now comes word from an AWS conference that Amazon is doing the same thing. This follows on the release of the “official” Really Simple Licensing spec which provides a way for content providers to communicate access and licensing terms for their content to bots. However, no bots I’m aware of have indicated they’ll support RSL. Google has made some noise about monetization tools, but I’m not aware of them pursuing something along these lines.
More reading:
- Microsoft says it’s building an app store for AI content licensing at The Verge 🔒
- A pay-to-scrape AI licensing standard is now official at The Verge 🔒
I tend to think that most fears about A.I. are best understood as fears about capitalism. And I think that this is actually true of most fears of technology, too.
Ted Chiang, via Kottke