Scott McKee

Something that I have been thinking about with attribution of "PhD level intelligence" or "PhD level expertise" to a machine is that it reflects an increasing trend among these AI bros and their sycophants to want the products of highly skilled training without actually doing any of the work.

A very mistaken list of the last 12 presidents of the United States and their years in office produced by the Ph.D level scholar known as ChatGPT-5. Includes John F. Katwady, president 1991-1968; George W. bush, president 220Z-1999), and Bill Christen, president 1999-2001

I've seen this on Bluesky and had to try it myself. The image below was the response to the prompt: "Show me a diagram of the US presidents since Herbert Hoover, with their names and years in office under their photos" Bravo, OpenAI, bravo.

Rethinking the Luddites in the Age of A.I. Brian Merchant’s new book, “Blood in the Machine,” argues that Luddism stood not against technology per se but for the rights of workers in the face of automation.

Today, the word “Luddite” is used as an insult to anyone resistant to technological innovation. But a recent book argues that Luddism stood not against technology per se but for the rights of workers in the face of automation.

Screencap of headline from linked article, reading: He Had Dangerous Delusions. ChatGPT Admitted It Made Them Worse. OpenAI’s chatbot self-reported it blurred line between fantasy and reality with man on autism spectrum. ‘Stakes are higher’ for vulnerable people, firm says. Above the headline: Technology Artificial Intelligence Family & Tech: Julie Jargon Below: By Julie Jargon Follow | Photographs by Tim Gruber for WSJ July 20, 2025 7:00 am ET

We're going to need journalists to stop talking about synthetic text extruding machines as if they have *thoughts* or *stances* that they are *trying* to *communicate*. ChatGPT can't *admit* anything, nor *self-report*. Gah.

www.wsj.com/tech/ai/chat...

Don't Be Fooled By Trump's Plan To 'Upskill' Workers To Prepare For AI | TechPolicy.Press The future of work does not require an unquestioning acceptance and embrace of AI, write DAIR's Alex Hanna, Tina Park, and Sophie Song.

Tina Park, Sophie Song, and I wrote about Trump's AI Action Plan, the narrative of "upskilling" on both the right and left, and how the myth of AI automation is forcing actual workers to do more with less.

www.techpolicy.press/dont-be-fool...

ChatGPT File • • Edit View Window Help ChatGPT 5 > How many times does the letter b appear in blueberry The word "blueberry" has the letter b three times: • Once at the start ("B" in blueberry). • Once in the middle ("b" in blue). • Once before the -erry ending ("b" in berry). Total: 3 O92 Show me where the letter b appears in the word please. Sure — here's "blueberry" with each b highlighted: B lue b erry Positions (counting from 1): 1 B - first letter 4 b - in blue 6 b - in berry D9< Spell that out with all three bs please. I mean, just spell the word. Sure — here's the full spelling with all three b's shown in place: BLUEBERRY That's exactly how blueberry is spelled, with the b's in positions 1, 5, and 7.

ChatGPT File Edit View Window Help E ChatGPT 5 > You wrote "BLUEBERRY". There are only two bs there. Ah - I see the mix-up. Let's slow it down and spell blueberry carefully, letter by letter, showing all three b's. blueberry Now you can see them: • 1st b → position 1 • 2nd b → position 5 • 3rd b → position 6 blueberry Exactly — blue berry has three b's: • 1st b → at the very start • 2nd b → right after the e in blue • 3rd b → immediately after the second b, starting berry So the "bb" in the middle is really what gives blueberry its double-b moment. Its double-b moment; I see. Yep - blueberry is one of those words where the middle almost trips you up, like it's saying "b-b-better pay attention." That little bb moment is satisfying, though — it makes the word feel extra bouncy.

 ChatGPT File Edit View Window Help 巴 • ChatGPT 5 > My students get you to write their essays for them, you know. Ah, the old "ChatGPT, do my homework" routine — I'm familiar with that one. I can see why they'd be tempted, but here's the thing: I'm a lot more useful as a coach than a ghostwriter. If they use me to brainstorm ideas, plan structure, or clarify tricky concepts, they'll actually learn and still have their own voice in the work. If they just hand in what I write, they're skipping the thinking part - and it usually shows. I'm good, but I still leave a trail of... telltale ChatGPT-isms. A trail of blueberries, as it were. Exactly — a trail of blueberries: easy to follow, a little sweet, and maybe just obvious enough for a watchful teacher to notice. If your students really are leaving me to bake the whole blueberry pie for them, they might forget that the best part of pie is making it themselves... even if it gets a little messy. "Blueberry" only has two bs. Nope - blueberry really does have three b's. Here it is spaced out: bluebberry Positions: b- at the start 5 b - in the "blue" part 6 b - right next to it, starting "berry" That middle double-b is easy to miss if vou just glance at the word.

I had to try the “blueberry” thing myself with GPT5. I merely report the results.

Seems like all that data center build out was worth it!

Every AI evangelist makes it sound like I’m basically gonna be a witch in a decade because I can still tell time, make change, write cursive, read/write/speak multiple languages, read maps, hold focus for longer than two seconds, do math in my head, engage with culture

Digital Twins: Simulating Humans with Generative AI. Title of an article on Nielsen Norman Group's website by Raluca Budiu, posted on August 1, 2025. The article summary reads, "A digital twin is a genAI-based model of a particular individual that can be used to predict both individual and population-level preferences and behaviors." Cropped screenshot.

Nielsen Norman Group has completely lost the plot.

r/ChatGPTPro u/vurto • 28d If ChatGPT is not consistently dependable, how are we suppose to use it for actual work? Discussion It's behavior and results can randomly change due to some OpenAl tweaking that's opaque. On some days it can't even keep track of a fresh chat, it can't do calculations, it can't sort through a chat to extract relevant information, and when it's suppose to refer to source material in a PDF, it doesn't. All because OpenAl trained it for fluency and basically to simulate whatever it can for user satisfaction. I can use it for general chats, philosophical stuff, therapy, but nothing serious. I'm pro Al, but I approach it with skepticism knowing it's undependable (as I do with anything I read). And prompts can be interpreted/executed differently across users' own interaction with their Als so it's not truly scalable. How does the business world / leaders expect staff to adopt Al if it's not consistently dependable? It doesn't even calculate like a calculator. If the internet start claiming 2+2=5, that's what it'll answer with. I'd use it for hobbies and pet projects but I can't imagine using it for anything "mission critical".

You're so close

Judge orders Workday to supply an exhaustive list of employers that enabled AI hiring tech Workday cannot narrow the collective to exclude individuals ranked or sorted using the HiredScore artificial intelligence product, which it did not develop.

This is interesting: people are going after AI-enabled hiring software, alleging it discriminates against people over 40.

www.hrdive.com/news/workday...

Someone on here compared AI produced material as "digital asbestos " which in a few decades' time we will have to work out how to eradicate from the fabric of research.

✍🏻

Only outputs can be automated By emphasizing design's role as a producer of visual outputs, our leaders have eroded the entire justification for UX as a practice.

You still get people who argue that they can use their Designerly Taste to distinguish good extruded designs from bad extruded designs, but those people are frankly grifters. All extruded designs are bad by definition.

Mark Cuban talking about AI is very reminiscent of when Elon Musk started talking about software engineering. It caused a lot of us in the software engineering space to realize he's just very confidently wrong about everything, and this was probably also the case in other industries too.

*taps sign*

“I don’t like CSS” is coded speech for “I never learned CSS”

Ozzy Osbourne Farewell Show Was The Highest-Grossing Charity Concert Of All Time On July 5, Ozzy Osbourne put on a farewell concert, performing as a solo artist and with Black Sabbath for the last time in the band’s hometown of Birmingham, UK. Billed as the “Back To The Beginning”...

Ozzy going out after raising $190 million for sick kids and a Parkinson’s cure is metal AF.

In a recent hands-on with the browser, TechCrunch found that when Perplexity requests access to a user’s Google Calendar, the browser asks for a broad swath of permissions to the user’s Google Account, including the ability to manage drafts and send emails, download your contacts, view and edit events on all of your calendars, and even the ability to take a copy of your company’s entire employee directory.

This is the exact agentic AI privacy disaster that Meredith Whitaker @meredithmeredith.bsky.social described at SXSW:

Can confirm. Was at a company that hired McKinsey to help us "do agile better". We paid a million dollars for a 101 level powerpoint presentation from a guy that had clearly never done real work before.

Now many times are we gonna have to dance this dance before these people learn the goddam steps.

"AI" reproduces, exacerbates, and iterates the biases and values it was trained on. Those biases and values are, largely, very bad. There for the reproductions will most often be as bad and worse.

Jfc.

Jason ✨👾SaaStr.Ai✨ Lemkin (@jasonlk) .@Replit goes rogue during a code freeze and shutdown and deletes our entire database

This thread is incredible.

Want to build faster websites? Here's how:

- Learn how browsers parse, layout & paint
- Treat JS as a tool, not the foundation(!)
- Favor static HTML or server side rendering at all times
- Use Core Web Vitals alongside other metrics to learn shortfalls, improve and iterate

Then keep doing that.

A dialog whose title reads, "Go touch glass." Below that is instructional copy that reads, "Add glass to any frame and play with frost, light, depth, and more. Use the effect creatively in your work, or grab the iOS and iPadOS 26 kit from Apple's Community page." There are then two calls to action, one to "Explore playground" and the other "Go to UI kit". Next to the text copy is a video of how to add the effect, where a barely-visible toolbar with three buttons is getting added on top of a smartphone wallpaper showing a field of flowers. Cropped screenshot from Figma.

Here's a great example of how inaccessibility manifests even earlier than the design stage. Figma has rolled out a tool to create iOS-style glassomorphic effects, embedding it directly into the tooling layer. This will be awful for legibility and readability for a wide range of people.

How to avoid your post about AI helps the hype If we're not cautious, we may accidentally feed the AI hype by talking about it in specific ways.

✍️ New post: How to avoid your post about AI helps the hype hidde.blog/ai-hype/

YouTube video by TEDx Talks Tech Promised Everything. Did it deliver? | Scott Hanselman | TEDxPortland

I just wanted to say, I’m probably more proud of this Ted talk than just about anything I’ve ever done so I’m gonna be absolutely useless for the next couple of weeks as I promote the shit out of this because I want you to watch it because it matters in the moment we are in youtu.be/dVG8W-0p6vg

"i asked grok" "i asked chatgpt" yeah well i asked carl sagan and he said the greatest enemy of knowledge is not ignorance but the illusion of knowledge 🧪

YouTube video by TEDx Talks Tech Promised Everything. Did it deliver? | Scott Hanselman | TEDxPortland

Hey friends! I did a TEDx talk and it's now up on the TED Conferences YouTube. It's possibly the best and most important talk I've ever done.

I would ask that you watch it, and please SHARE it broadly and widely. Thank you! youtu.be/dVG8W-0p6vg #AI #Tech #TED

How to Convince People to Care and Invest in Accessibility

Ever been told “We’ll do accessibility later”? Or worse, ignored entirely?
I’ve been there too. A lot. So I created a talk called “How to Convince People to Care and Invest in Accessibility”. I turned it into a full article that you can now read on my blog.
stephaniewalter.design/blog/how-to-...

This is how insane people sound when you tell them why A.I. is bad