Designing systems and interfaces. Opinions are mine, etc. https://xitter.gq/t.co/p6X7vbrnaI
Poland
Joined January 2007
- Tweets14.5K
- Following123
- Followers976
- Likes3.5K
It’s crazy how this little assistant gave me back agency in my day-to-day. I’m not going to list examples because they don’t matter that much + they’re very specific to the kind of life I lead, but having a box I can just talk/type stuff into and it does things… so useful.
I’m really glad I got to grow up with Star Trek. Captain Picard gave me a model of integrity, curiosity and decency at an age when I didn’t always have that kind of guidance at home. I think some of the man I became came from watching him. Farewell, Sir Patrick Stewart.
OpenAI Dot is the first assistant/companion I’ve tried, and it’s pretty good. It definitely helps me conserve my decision budget.
I just wish it was a separate app. When I open ChatGPT on iOS or Codex on macOS, I have a different job in mind than checking what my Dot is up to.
It’s so crazy that Codex just did not increase the context window to ~1M when I upgraded my seat to Premium. In Claude Code, a Max plan just did that automatically, and here I had to… ask it? And the setting is a dotfile? Are we for real, OpenAI?
… wants to add a helper
… would like to access files
allow … to find devices on local networks
background items added
Does anyone think these permission prompts / notifications make anyone safer? Where’s "Auto" setting for people who just want to use their computer.
This is going to sound petty but watchOS 27 changed my favorite watch face making it monochromatic. I don’t understand how a company can claim they’re in the fashion industry and a software update breaks a piece of flair someone looks at 50 times a day.
I have no shortage of plans for adapting to what AI is doing to my industry.
What I don’t have yet is an answer to "how much can you change the nature of your work before you also have to change something fundamental about yourself?"
"The engineering job used to be rowing, and now it's steering. There's a lot of people out in the world right now that are like, I don't want to f*cking steer. I want a row. I liked rowing." — @molly_g
The only assistant I want is something to enable superhuman memory: instant recall across my chats, notes, docs, etc.
Another inbox to process? Sounds like work. 🥱
The problem with all of these AI personal assistant things is that people don’t actually want to do stuff.
You fucking get that right? Do you understand that?
Just like AI tools in the workforce, AI assistants don’t actually abstract decisions for you, they let you accelerate decision making.
So instead of making one decision a day and then lamenting you can’t do more, AI assistants are going to let you make ten decisions a day and act on all of them.
A miracle?
Nah dog, a fucking nightmare. Nobody except type A strivers who need Twitter fodder actually want that.
Let me tell you a story.
When I got back from college I was inspired. If I could take on an elite university with grit and determination, so could everyone I know.
I was all razzed up to get people I know to achieve their potential. What I learned after many years of trying is that absolutely nobody wants to realize their potential.
People want to hang out with friends and complain. That’s how the world has worked for ten thousand years. This weather fucks. Can you believe the cows walked off.
People don’t want enablement. People don’t want you to take all of their excuses.
TV is mindless passive activity. AI assistants are not. They’re telling people that they can achieve more. And people absolutely do not want that.
Let me tell you another story.
Once upon a time I lead a big process overhaul at work and it was great. Two years later I hired a contractor to do something similar. But I personally didn’t want to have to do a bunch of work.
Within a week I knew I fucked in. This contractor kept coming to me with decisions I needed to make. Dude I wanted to not have to think about this.
Again, a helper when you don’t actually want help is a disaster.
None of these AI assistants will take off because people don’t actually want assistants.
Look on my ancient workflow, ye trends, and cope:
It still works. That was always the whole point.
Introducing Elyx.
A better source of truth for design engineers and agents.
A place where design means more.
elyx.design/
Played with Astra all weekend on my Team plan with standard seats, and while it’s unfortunately too expensive to justify for personal projects, it’s so damned impressive. And FAST.
I don’t know what AGI is exactly, but if you’d shown me this 5 years ago, I’d have freaked out
My rule is simple: if you give me 100% generated text to read with no edits of your own, I’ll 100% feed it to my agents for processing / scheduling work without reading it myself. Expecting anything else is insanity at this point.
The revolt of the reader
bcantrill.dtrace.org/2026/09…
Too little has been said how goofy Claude’s default font choice is. I rarely read anything it summarizes in more than 3 paragraphs because it’s pain. Line-height is too small, letters are blending together. Overuse of bold, monospace and italics doesn’t help.
I always knew I couldn’t work in an office and now it’s truly impossible… I’ve become the person I used to hate: speaking into a headset all day while everyone else puts on noise cancelling headphones.
“Geppetto, let’s redo padding on that sidebar…” smh
Surely @OpenAI still hasn’t added workspace/org switching to Codex because they’re afraid folks will make 10 accounts and swap between them when hitting limits and those plans are heavily subsidized so even more lost money? I just want to switch between work and personal GPTs…
Some technical friends push back on LLMs by telling me to “use my brain” and find the answers myself. I would, if “the internet” still meant what they think it means. The thing we have now is hostile to attention and barely usable.
The web… sucks. I hate it.
I understand the need to test UI changes but honestly, when AI labs do this all the time to their model picker I just feel like they want to trick me to accidentally use a lesser model.
Peter 🇵🇱🇺🇦 retweeted
I've used em-dashes my whole life — they add rhythm and grace to writing. But now they're an AI tell.
Can we get a grandfather clause for those of us who were fluent in em-dashes before ChatGPT launched in November 2022?