Treating an AI agent like a person stops you checking its work, and that would still be a problem even if these systems turn out to have an inner life - which I get at by way of our vacuum robot, a colleague's AI intern, and an engineer who says you should never test your agents.
I taught the engine to blend Mastodon and Bluesky replies into one comment thread, and picked up local search, lighter images, and dark mode on the way.
Seven books finished across June and July, three of them excellent, and the same complaint about every one that missed - it went on too long.
DevRel isn't really about selling anything - it's about building a whole ecosystem so big that we can barely measure its growth because a rising tide lifts all boats.
It's funny how I got so bored of taking pictures that were just 'pretty,' forcing me to learn how to make the camera show things - like light, or movement, or multiple viewpoints - that nobody could actually see.
The meaning of a photograph gets made by whoever is looking, and never quite where you would have bet. For a while that felt like being written out of my own pictures. It turns out to be the whole job: you build the occasion as well as you can and hand it over, and making it for yourself is the only way to make it worth receiving.
The argument about whether AI photography counts is old and boring; the question worth having is where a photograph gets its meaning - and whether a machine that can make meaning too quietly writes the photographer out of the conversation. The same tool points two ways, and what settles which is whether you had something to say before you opened the box.
Every story the camera industry tells is a claim about the picture, and most of them fall apart when you check. The gear that has actually changed anything for me changed how I behave instead, which is the part no product page can show you.
Almost everything we believe about photography arrived without ever being examined: the good light, the sharp frame, the lens that supposedly sees the way we do. What is left when you stop accepting the defaults, and why the shape of a photograph belongs to whoever is making it.
A year of #fotogedanken, distilled into one piece: photography is a practice you do for yourself, in a world that keeps insisting it is for an audience, a platform, or a purchase.
If you shoot anything outside of standard visible light - like deep infrared or UV - you need to know which demosaicing algorithm is actually going to save your image from turning into a colorful mess of artifacts.
Honestly, you can't just click through tutorials for this stuff because everything - from setting the white balance to choosing a demosaicing algorithm - requires manually overriding what the software thinks is right, which means abandoning your favorite easy-to-use program entirely.
I ran a full comparison of nine different models - from remote giants to my local setup - and found that how finished your draft is matters way more than which model you pick, especially when privacy and speed are non-negotiable.
I rebuilt my blog engine to make sure that everything you see here is transparent, private, and free from third-party tracking.
We woke up to Ontario buried in wildfire smoke again - and all I can really do is watch it become normal and be frustrated that leaders won't act.
A small toolkit of habits for using AI honestly - tagging what it touched, owning what you ship, and setting the tool up to poke holes in your thinking instead of flattering it.
I experimented with ditching the all-in-one smartphone for specialized gadgets like smartwatches and e-ink readers to maintain modern convenience while reclaiming personal focus and time autonomy.
Soccer stars use their skin as a permanent canvas, adorning themselves with tattoos that chronicle personal milestones, legendary status, and athletic rivalries.
A look at why I built a minimalist local-first static site generator powered by simple Python scripts, AI, and Markdown.