Daily Reading List – May 13, 2025 (#551)

I don’t know the “future of coding” with AI, but there are sure a lot of opinions out there. I was in a few forums today where it came up, and I’m seeing so much discussion on the interwebs. Even if you can have AI do all our coding, would that be what we want? I doubt it.

[article] Coding LLMs from the Ground Up: A Complete Course. Great links to videos here for those that want to truly learn the fundamentals of how LLMs work.

[blog] Evaluate your gen media models with multimodal evaluation on Vertex AI. I really like this. Here’s a way to evaluate whether AI-generated images and video meet your intentions.

[blog] Cloud Run and the Identity Aware Proxy. Here’s a great walkthrough of the new, easier way to secure web apps for internal or external users.

[blog] Coding should be a vibe! Even if people can “give up” coding in favor of agents doing it, is that what we want? DHH doesn’t seem to think so.

[article] Coding Assistants Threaten the Software Supply Chain. As you use capabilities like MCP or pre-defined “rules”, be careful of new attack vectors.

[blog] Graceful Shutdown in Go: Practical Patterns. Are you good at graceful shutdowns for your apps and systems? Here’s some good advice, even if you aren’t writing these patterns in Go.

[blog] Gemini Global Endpoint: Enhanced Availability for Your AI Applications. This is useful for those scenarios where data residency doesn’t matter, and performance does.

[article] What nobody tells developers about documentation. Your software or app needs docs and developers should care a lot about what’s written for their product.

[blog] Real-Time Vehicle Telemetry with Synadia Cloud and Google Cloud Bigtable. Cool demo and a great way to understand how you might feed remote telemetry into a query-able datastore in near real time.

[blog] Bringing 3D shoppable products online with generative AI. Video seems poised to explode, even more that it already has. The use of Veo to create 3D objects is terrific.

[blog] Benchmarking LLMs: How We Actually Know What’s Good. Get familiar with a few of these, and build some skill at evaluating models yourself.

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