Daily Reading List – January 5, 2026 (#693)

Back to work after a two week holiday hiatus. I enjoyed the time off, but also looked forward to getting into the game again.

[blog] Your team has a context window. Our working memory gets full too, just like an LLM. What’s the impact on team performance when you force people to hold too much information in their heads?

[blog] The State Of LLMs 2025: Progress, Problems, and Predictions. There wasn’t a single breakthrough moment last year for AI, but an ever-growing set of milestones that moved everything forward. Terrific look back from Sebastian here.

[blog] 13 of the best Nano Banana trends from 2025. These are all great. Just tried a couple of them. Do more things for fun this year.

[blog] How I think about Kubernetes. Is it “just” a container orchestrator? Or is Kubernetes a runtime for declarative infrastructure? This post argues for the latter.

[blog] Why I Write (And You Should Too!) Write to learn, to develop your voice, to create serendipitous moments. I’m a big proponent of learning in public.

[blog] Why Blogging Still Matters in the Age of AI. Related. Write for yourself, for others, and for your career. I attribute at least three jobs to having a public writing resume.

[blog] Code Quality Foundations for AI-assisted Codebases. I like these categories of rules and such that you can tell your AI tool to comply with. Seems like this would dramatically improve the quality of the generated codebase.

[article] VCs predict enterprises will spend more on AI in 2026 — through fewer vendors. Once the wide experimentation phase is done, it seems likely that bigger companies will compress their vendor list.

[blog] The importance of Agent Harness in 2026. I haven’t looked into this topic much, so Philipp’s post was educational for me.

[blog] The Silent Breakage: A Versioning Strategy for Production-Ready MCP Tools. You can really mess up your agents by changing tools in ways the agent isn’t ready for. These appear to be solid suggestions.

[article] MCPs for Developers Who Think They Don’t Need MCPs. These are good use cases, beyond a basic “stuff into my IDE” scenarios.

[article] 6 incredibly hyped software trends that failed to deliver. Some bangers here, all of which delivered some value. And “generative AI” doesn’t belong on the list yet.

[blog] How Good Is AI at Coding React (Really)? Can we move past “vibes” and really consider how well AI codes in certain situations? Addy does that here.

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