Daily Reading List – July 23, 2026 (#831)

You never know how a day will turn out when you’ve got a last-minute, vaguely-titled 1:1 with your CEO. It ended up being a good chat and I’ve got some fresh items to go tackle. It’s a treat working for leaders who know what they’re talking about, and want to win.

[article] Where the real competition is in AI. Fair assessment by Matt. Most of us want to be the place where AI-assisted work happens. Everything else is in service of that.

[article] How does adopting AI tools change developer burnout? Autonomy still matters. Read this for where burnout creeps in.

[blog] How Anthropic secures its AI-native software development lifecycle. If AI is authoring 80% of the code at Anthropic, how are they maintaining a credible security posture? This post goes into it.

[article] The Tokens You Can’t Wait For. Interesting read about diffusion models and the mechanics of GPUs. Worth a read if you’re figuring out your AI infrastructure strategy in a way that maps to your business needs.

[blog] How I built a skill to fan out 20 workers to fix my old Rails App on Antigravity (steal my prompt!). I enjoyed reading this journey from Riccardo. This is definitely a valuable pattern that you’ll see more of.

[article] Amazon, Microsoft, and Google are converging on the same enterprise agent architecture. Cloud Foundry got many things right. Cloud providers are doing some serious vertical integrations with echoes of former PaaS products. But there are differences.

[blog] How I Built a CLI That Saves AI Prompts in Git. Neat idea. It sort of complements the idea from my own post yesterday.

[blog] Open Reasoning Format: Building Self-Learning AI Coding Agents Without Server Infrastructure. Similar to above, we’re thinking about how to help agents (and teams?) save operational learnings across sessions.

[blog] Measuring AI ROI: The Next Big Conundrum for Enterprises. Just make sure you’re looking in the right places, and have done the “right” work to generate that ROI.

[blog] Prefactoring: Clear the Way for Your New Feature. Smart. Consider when you should get ahead of an upcoming change and make your life easier.

[blog] That You Must Suffer for Greatness is a Dangerous Lie. In virtually every case, you need to work hard to do something great. No way around that. But it can be enjoyable hard work, not necessarily “suffering.”

[blog] The hidden cost of Skills in AI Coding Agents. Skills aren’t free. You might spend more (or fewer) tokens or see extra operational overhead.

[blog] Model Context Protocol (MCP) vs. Agent2Agent (A2A): which protocol do you need? Here’s a look at each protocol and where they fit. It includes a look at what neither one addresses.

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: