Today's local Ai exploration is building a photography culling workflow on top of the Apple Vision framework models. Will do my best to also build a wrapper plugin for Lightroom

I don’t know if I agree with this take. Good frameworks are intelligence caches. The production of verifiable high-quality code has a cost to it (insert for now caveat). Frameworks can lower this cost as long as they don’t get in the way of agents.

IMO the only tests you should have in the age of coding agents are, in order of priority: 1. Full E2E tests. Nothing mocked out at all. Can even be something that runs in prod on test accounts via Playwright or equivalent. 2. Integration tests. Agents make more mistakes as things bleed between data/API boundaries where schemas can drift. 3. Golden tests. This helps ground the code with real examples of data, and can be used as regressions against edge cases. Unit tests are bloat 99% of the time if you’re using a frontier model since they’re smart enough now to get the implementation (and subsequent iterations) right on the first shot, so they only add bloat at this point.

Strands Decider 2B, a small, open-source decision model, perfect for experimentation but capable enough for real work: strandsagents.com/blog/intro… We've open sourced the whole recipe, with all the training data, code, and log of what we learned along the way: github.com/strands-labs/stra…

At this point the only acceptable tech stack IMO is Elixir for web and Rust for everything else. Give me 1 good reason to still use a JS framework (besides extremely simple marketing/portfolio websites)

If it works, if it's performant, if it has no bugs, if you understand how it works, if the agent can modify it a month from now, to your liking, is it slop?

What was your first version control system? Mine was… CVS->SVN->Git

A painful part of working with your data has always been that your live data and historical data are stuck in separate systems: the order a customer just placed lives in your database, while their last five years of orders sit in a data lake in S3. And answering a real question usually needs both at once (is this a normal purchase for them, or should we flag it?), and to do that you had to move the data together first, copying history out of the data lake into your database (or the other way around), because the database couldn’t read it where it lived. That meant guessing ahead of time which data you’d want, keeping a second copy of it all, building pipelines to move it, and constantly syncing so the two didn’t drift apart. A lot of plumbing, and slow going, all before you could answer one question. And even then, the answers were only as fresh as your last sync. That now changes with Aurora PostgreSQL, which can call your live data and historical data in S3 together, in a single query. No copying, no pipelines to keep in sync. And it’s fast, because we’ve built in DuckDB, a popular open source engine that’s really good at reading and analyzing data right where it’s stored. DuckDB reads the open formats like Parquet and Iceberg already sitting in your data lake, so there’s nothing to convert or move. As folks build AI agents into their apps, the data their agent needs will depend on the task in front of it. Being able to query that specific data live, instead of copying it over just in case, is gonna be a big help for builders. aws.amazon.com/blogs/aws/ama…

Most notably this design lets you INSERT + Produce an event into Postgres/Kafka in one atomic transaction. If the transaction aborts, nothing gets saved.

Artificial intelligence systems do not think, feel, want or understand. Avoid language that gives them human characteristics. This is called anthropomorphizing, when we ascribe human traits, emotions or behaviors to non-human things, such as animals or inanimate objects. Instead, explain what a system does, how well it performs, who built it and who could be affected by it. apnews.com/article/openai-sa…

Jev is coming for your garbage code comments

Best booth award at AFA 2026 goes to...