Hacker News Reader

ar_turnbullon AI-generated posters don’t have to be horrible

I’ve been working on a thing where a bunch of raw content goes through a summarization pipeline and then gets manipulated with a bunch of checks to clean up copy and reduce clutter.

And then the visuals get added with a set of fixed templates. It’s not fully there but is reducing a LOT of the clutter.

Some of the results are even what I’d call good (and I’m a designer). I think a good harness could make non-cluttered results, if one of the AI labs was interested in a “less is more” approach.

ar_turnbullon qm – Multiplayer agent harness for work

Also feels copied from impeccable.style (which I think was the original anti-slop skill).

ar_turnbullon Using Claude Code: The unreasonable effectiveness of HTML

If it’s a collaborative doc, you could make a pretty quick WYSISWYG or markdown editor for inline editing.

I’ve done something similar with Figma-like commenting and find myself pulling it into all kinds of personal projects.

ar_turnbullon Using Claude Code: The unreasonable effectiveness of HTML

I’ve been prompting my way to all kinds of interactive HTML artifacts the last month or so. It’s way more fun than making decks and static documentation.

I even did a workshop with PartyKit cursors, dot voting, reflection comments, and an individual rating at the end.

Oh, and I can add super lightweight analytics so I know who actually reads my things or interacts with my prototypes. ^_^

ar_turnbullon Sherry Turkle: "We're losing the raw human part of being with each other" (2013)

Heh. Same here. I had the same reaction to “everybody likes Facebook.”

ar_turnbullon Slop Cop

Interesting. I made a skill for my Claude agent based on Wikipedia’s list of AI writing tells. /remove-ai-writing

It works reasonably well (better if you run it a few times), but still benefits from a final pass by a human editor IMO.

https://github.com/arturnbull/remove-ai-writing

ar_turnbullon Google releases Gemma 4 open models

Following as I also don’t love the idea of double paying anthropic for my usage plan and API credits to feed my pet lobster.

ar_turnbullon Show HN: E is for ENSHITTIFICATION – An illustrated children's book on big tech

A little more background:

Around this time last year I shared a talk on Enshittification, discussing what it means for design and technology professionals. Somehow it ended up being the #1 talk of the conference... so my team got to talking about how to build on it.

We felt like a children's book was just the right mix of irreverence, cheekiness, and fun to make this complex, systems-level topic more accessible for people.

It's a real children's board book with colourful illustrations printed on thick cardboard pages. The team had a LOT of fun putting it together — debating what each letter should be and how best to illustrate it.

And it's been a surprisingly useful tool for connecting with like-minded individuals in tech!

My fav letter: X (which of course, is for Twitter — RIP sweet bird)

Most difficult letter: K (after many discussions, we landed on K-shaped economy)

Longest word: Verschlimbessern (borrowed from Pavel Samsonov of The Product Picnic... the German's have the best words)

ar_turnbullon RSS.Social – the latest and best from small sites across the web

Oh this is neat. Explains why I’ve seen a few Kagi referrals in my analytics.

Thanks for your work on this. It’s appreciated!

ar_turnbullon Show HN: Figma-use – CLI to control Figma for AI agents

Thanks. Definitely planning on checking this out!

If I’m understanding correctly, you’d likely combine this with Figma MCP for reading? Ie. have Claude Code read the file to understand a request, then use this tooling to make modifications?

ar_turnbullon Ask HN: Share your personal website

https://www.andrew-turnbull.com

Portfolio site and writing that explores Product leadership, UX Design, and the overlap between the two.

ar_turnbullon Resources that helped me bridge the gap between UX and Product thinking

Over the last year I’ve been exploring the overlap between UX and Product leadership, and the growing tension between the two. I've compiled a list of books, talks, and other resources that helped me make sense of the divide. Sharing in case it's useful for others working across design and product.

ar_turnbullon Pieces of Career Advice I Wish I'd Known Earlier

> The thing I’ve learned about leveling up in your career, or breaking through different ceilings, is that you really only realize that it happened in retrospect. Just like you don’t notice your hair growing or your face aging, you can’t really feel it as it’s happening. Be patient—evaluate later. Don’t kick yourself now because you think you’re stuck. You might be the opposite of stuck and just not know it.

—-

This one resonates hard for me right now. Having spent the last year feeling stuck, I’m finally starting to see the path out (I’m a UXer moving towards Product leader roles). I’ve spent a lot of time kicking myself, and now all of a sudden it’s starting to feel like I might be on the other side.

ar_turnbullon The Modern Career

This is a cool explanation, great visualization.

One note — on mobile the sticky section feels a bit tall making reading experience a bit clunky — maybe just screenshots from the simulation would do the trick, rather than live states?

Either way, looks great — nice work! Curious if the data shows anything about successful strategies, or if this could be simulated as well (ie. join an early stage company, get an MBA, etc).

ar_turnbullon Web development is fun again

As someone who always dabbled in code but never was a “real” developer, I’ve found the same thing. I know the concepts, I know good from bad — so all of a sudden I can vibe code things that would have taken me months of studying and debugging and banging my head against the wall.

If you’ll forgive a bit of self promotion, I also wrote some brief thoughts on my Adventures In AI Prototyping:

https://www.andrew-turnbull.com/adventures-in-ai-prototyping...

ar_turnbullon Japan's 'Dementia Money' Is a Warning to the World

Definitely worry about this with my mother-in-law. I cleaned the malware off her computer yesterday because she was complaining that "google was broken" and that "every time it filled the screen with advertisements."

I don't really know what to do about it, but dementia + lack of technical understanding + lack of security best practices + retirement funds are, without doubt, going to be a huge problem in the coming decades.

ar_turnbullon Pocket Brain – offline AI chat that runs in the browser (WebGPU)

Just curious whether it would it make more sense as an app (even if it's just a wrapper)? Is that on the road map? I know technically you can download large files in the browser but do normal people understand that?

On iOS with memory management, I always find that browser pages always feel.. brittle?

ar_turnbullon I Study Friendship. Here's How You Make Lasting Friends.

TLDR; - Look for friendship markets, not just activity groups - People are most open to new friendships when people are redefining themselves (i.e. school transitions, pregnancy, shifting identities). - You're not awkward, you're just searching in the wrong markets where people are open to conversation but not connection.

ar_turnbullon Show HN: I built an AI optimized for venting, not working

Ya ditto — I’m not sure why I’d use this compared to a new chat with some specific instructions in chatGPT.

The idea is novel and has a great hook IMO, but it needs something that lasts beyond the initial hook.

When I tried a rant the response was.. ok but generic, and definitely not sticky.

ar_turnbullon Anti-Aging Injection Regrows Knee Cartilage and Prevents Arthritis

Wow. This is legit very cool. Hopefully it can be made widespread just in time for a cohort of aging millennials like myself.

ar_turnbullon Finger-Nose Stylus for Touch Screens (2011)

Thanks.

ar_turnbullon Take One Small Step

Felt the same to me too ¯\_(ツ)_/¯

ar_turnbullon Total monthly number of StackOverflow questions over time

End of an era. :-(

ar_turnbullon Elegance is Bullshit

Haha you’re right — “quiet discipline” is quietly giving it away.

ar_turnbullon The suck is why we're here

The point about recognizing what’s valuable and making sure you don’t outsource that resonates.

The other day I was on LinkedIn and a Chief Design Officer at a notable company posted her reflections on leadership for the year. There were some potentially interesting insights, but they never got past a surface level. The AI-ness of the writing was as clear as day (and GPTZero tagged it as 100% likely to be AI).

It’s disappointing when you see leaders and so-called stewards of taste farming out that part of their voice.

ar_turnbullon Disc Brakes Took over the Cycling World. Here's Why That Was a Mistake

Ehhh. Rim brakes are cheaper, that’s true. They’re easier to adjust as well.

There is absolutely nothing wrong with a road bike with rim brakes on it.

But so long as they’re set up properly, discs are also nice - and far more confidence inspiring.

ar_turnbullon Apple Detection of Flashing Lights

There’s an online test called the Harding Test that’s the standard now. It’s required for broadcast media in the UK.

ar_turnbullon Apple Detection of Flashing Lights

I was so happy and pleasantly surprised to see this feature come out today! I just spent the last week telling a client they can’t put their flashy new brand video on their website and still meet AA guidelines.

I told them to do a Harding Test and get the company who made it to do the edits because WCAG doesn’t leave any wiggle room when it comes to potential seizures (rightfully so).

Glad to see Apple leading in this front. These features aren’t sexy but they make a real difference in people’s lives!

ar_turnbullon Apple Detection of Flashing Lights

There’s this chrome plugin for YouTube videos. It stops the video before trigger scenes so you might find it a bit interruptive depending on your (or your cat’s) sensitivity.

https://chrome.google.com/webstore/detail/seizafe-epilepsy-a...

ar_turnbullon Mistakes I made as an engineer, but had to become a manager to see

Not sure if you've read Chris Hadfield's book (Astronaut's Guide to Life On Earth) but he talks about a similar system. In his words you can be one of three team members:

A Negative One -- You're a drain on the team and other people have to cover for you. Not so good if you're in space with limited resources.

A Zero -- You're capable and have your own shit covered. Most people in space are a zero.

A Plus One -- You're contributing to the success of the mission and helping others succeed as well.

He talks about arriving on the international space station and just making sure that he was a zero. And taking over as mission commander and on the first couple days, just trying to be a zero because the plus one fancy heroics can come later.