Michael Zimmer's Avatar

Michael Zimmer

@michaelzimmer.bsky.social

Privacy & data ethics scholar. Professor in Computer Science and Director of @MUDataEthics.bsky.social at Marquette University. I also curate @ZuckerbergFiles.bsky.social

2,336 Followers  |  394 Following  |  312 Posts  |  Joined: 25.08.2023  |  2.0291

Latest posts by michaelzimmer.bsky.social on Bluesky

Screenshot of a ChatGPT 5 query asking for a list of berries organized by the number of Rs in their name, and the result that shows mostly incorrect answers.

Screenshot of a ChatGPT 5 query asking for a list of berries organized by the number of Rs in their name, and the result that shows mostly incorrect answers.

More #Blueberry ChatGPT nonsense.

08.08.2025 16:54 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
It Looks Like a School Bathroom Smoke Detector. A Teen Hacker Showed It Could Be an Audio Bug A pair of hackers found that a vape detector often found in high school bathrooms contained microphonesβ€”and security weaknesses that could allow someone to turn it into a secret listening device.

A couple of years ago, a curious, then-16-year-old hacker named Reynaldo Vazquez Garcia found what seemed to be a β€œsmart” smoke and vape detection gadget in his school called the Halo 3C. He discovered it monitored much more than just smoke.

08.08.2025 13:23 β€” πŸ‘ 511    πŸ” 168    πŸ’¬ 17    πŸ“Œ 16

Friend one: β€œIs there even any point to applying to a Fulbright?”

Friend two: β€œWell, they’re accepting applicatio…wait a minute. Says they’re β€œprioritizing American Studies in light of the country’s 250th anniversary.”

Friend one: β€œI …don’t think they know what β€˜American Studies’ means.”

08.08.2025 03:55 β€” πŸ‘ 108    πŸ” 14    πŸ’¬ 4    πŸ“Œ 0
ChatGPT File
β€’
β€’
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:
β€’ Once at the start ("B" in blueberry).
β€’ Once in the middle ("b" in blue).
β€’ Once before the -erry ending ("b" in berry).
Total: 3
O92
Show me where the letter b appears in the word please.
Sure β€” 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 β€” 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 β€’ β€’ 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: β€’ Once at the start ("B" in blueberry). β€’ Once in the middle ("b" in blue). β€’ Once before the -erry ending ("b" in berry). Total: 3 O92 Show me where the letter b appears in the word please. Sure β€” 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 β€” 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:
β€’ 1st b β†’ position 1
β€’ 2nd b β†’ position 5
β€’ 3rd b β†’ position 6
blueberry
Exactly β€” blue berry has three b's:
β€’ 1st b β†’ at the very start
β€’ 2nd b β†’ right after the e in blue
β€’ 3rd b β†’ 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 β€” it makes the word feel extra bouncy.

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: β€’ 1st b β†’ position 1 β€’ 2nd b β†’ position 5 β€’ 3rd b β†’ position 6 blueberry Exactly β€” blue berry has three b's: β€’ 1st b β†’ at the very start β€’ 2nd b β†’ right after the e in blue β€’ 3rd b β†’ 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 β€” it makes the word feel extra bouncy.

ο£Ώ ChatGPT
File Edit View Window Help
ε·΄
β€’ ChatGPT 5 >
My students get you to write their essays for them, you know.
Ah, the old "ChatGPT, do my homework" routine β€” 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 β€” 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.

ο£Ώ ChatGPT File Edit View Window Help ε·΄ β€’ ChatGPT 5 > My students get you to write their essays for them, you know. Ah, the old "ChatGPT, do my homework" routine β€” 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 β€” 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 β€œblueberry” thing myself with GPT5. I merely report the results.

08.08.2025 00:03 β€” πŸ‘ 8906    πŸ” 2381    πŸ’¬ 479    πŸ“Œ 918

This is the way.

08.08.2025 03:43 β€” πŸ‘ 943    πŸ” 160    πŸ’¬ 5    πŸ“Œ 2

When student newspapers have clearer and bolder moral vision than university leaders.

07.08.2025 02:11 β€” πŸ‘ 102    πŸ” 31    πŸ’¬ 1    πŸ“Œ 1
Preview
Hackers Hijacked Google’s Gemini AI With a Poisoned Calendar Invite to Take Over a Smart Home For likely the first time ever, security researchers have shown how AI can be hacked to create real world havoc, allowing them to turn off lights, open smart shutters, and more.

NEW: In a likely first, security researchers have shown how generative AI agents can be hijacked to cause physical consequences.

They tricked Google's Gemini AI into turning off smart home lights, opening windows, and turning on a boiler.

They hid instructions to the AI in a *calendar invitation*

06.08.2025 13:55 β€” πŸ‘ 570    πŸ” 329    πŸ’¬ 21    πŸ“Œ 118
Preview
Wikipedia Editors Adopt β€˜Speedy Deletion’ Policy for AI Slop Articles β€œThe ability to quickly generate a lot of bogus content is problematic if we don't have a way to delete it just as quickly.”

www.404media.co/wikipedia-ed...

05.08.2025 17:27 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

A reminder that Meta (and anyone with a six legged horse in the AI race) needs as many people as possible wearing smart glasses capturing real world video for training world models.

05.08.2025 16:00 β€” πŸ‘ 287    πŸ” 97    πŸ’¬ 18    πŸ“Œ 5
Video thumbnail

Let this clip bring you the fire you need this evening πŸ”₯

05.08.2025 00:15 β€” πŸ‘ 4    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Preview
What the Columbia Settlement Really Means

The Columbia settlement is an β€œastonishing transfer of autonomy and authority to . . . an administration whose disdain for the values of the academy is demonstrated anew every day.” New @knightcolumbia.org analysis of the Columbia settlement, just published. knightcolumbia.org/blog/what-th...

04.08.2025 14:20 β€” πŸ‘ 499    πŸ” 231    πŸ’¬ 13    πŸ“Œ 22
Context Matters - CSCW'25 Context Matters: Ethical Challenges in Research with Online Communities

The full-day, hybrid workshop is "Matters: Ethical Challenges in Research with Online Communities" led by Matthew Zent plus @schancellor.bsky.social, @cfiesler.bsky.social, @sarahagilbert.bsky.social, @estellesmithphd.bsky.social and more.
sites.google.com/umn.edu/cont...

04.08.2025 20:18 β€” πŸ‘ 7    πŸ” 4    πŸ’¬ 0    πŸ“Œ 1
Context Matters - CSCW'25 Context Matters: Ethical Challenges in Research with Online Communities

The paper is "In Search of 'a Way to Level the Playing Field': Helping Incidental Users Navigate Privacy Risks in Smart Environments" led by Sunyup Park with @vitak.bsky.social & Nidhi Nellore. Our interviewees felt resigned to smart device surveillance & wanted transparency + owner responsibility

04.08.2025 20:18 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Grateful to be a co-author on a paper accepted to #CSCW2025, and excited to be part of a pre-conference on ethics in online community research. Sadly, I likely won’t make it to Bergen, as I’ll be at #AoIR2025 just the week before, 10,000 km away. A Rio-to-Bergen detour is a bit too much this time.

04.08.2025 20:03 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

I don't care what happens to my dead body since i'll be dead and who cares but please never do this to me

04.08.2025 19:48 β€” πŸ‘ 878    πŸ” 89    πŸ’¬ 40    πŸ“Œ 5

Today I'm working on an NSF annual report rather than actual research. #BureaucracyWins

03.08.2025 21:22 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Smithsonian removes Trump from impeachment exhibit in American History Museum A temporary placard, on display since 2021, described the president's historic impeachments. Officials said the exhibit was restored to an earlier version following a review of legacy content.

Newspeak.
www.washingtonpost.com/entertainmen...

31.07.2025 22:43 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
The great rewiring: is social media really behind an epidemic of teenage mental illness? Nature - The evidence is equivocal on whether screen time is to blame for rising levels of teen depression and anxiety β€” and rising hysteria could distract us from tackling the real causes.

As we talk about the cheerful insanity of Australia's Social Media Ban again this morning, here's your periodical reminder that the book it's inspired by - The Anxious Generation - is hogwash.

Not just me saying it, but this little journal you might have heard of: Nature.
www.nature.com/artic...

29.07.2025 22:57 β€” πŸ‘ 106    πŸ” 73    πŸ’¬ 6    πŸ“Œ 5

Each sentence gets increasingly absurd.

29.07.2025 04:50 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Faculty Support of George Mason’s President Draws Federal Investigation

Faculty who wrote to defend their president and object to a DOJ investigation of their university...are now being investigated by the DOJ.
The most banal defense of free speech and academic freedom will trigger the full wrath of the US government now.
www.nytimes.com/2025/07/28/u...

29.07.2025 00:23 β€” πŸ‘ 3884    πŸ” 1704    πŸ’¬ 105    πŸ“Œ 183
Cartoon with corporate media asking U.S. Government how it would like "Control of Internet Speech" wrapped: Anti-terrorism or protect kids

Cartoon with corporate media asking U.S. Government how it would like "Control of Internet Speech" wrapped: Anti-terrorism or protect kids

t's amazing how this is from more than 20 years ago but very well could have been from today.

28.07.2025 20:44 β€” πŸ‘ 13464    πŸ” 5139    πŸ’¬ 63    πŸ“Œ 60

Maybe it's irresponsible to leave critical systems to tech companies?

(Cc @faineg.bsky.social in case you hadn't seen this one.)

28.07.2025 07:19 β€” πŸ‘ 101    πŸ” 31    πŸ’¬ 2    πŸ“Œ 2

Well the choice was between cancer research and getting rid of pronouns.

27.07.2025 05:02 β€” πŸ‘ 5    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

It's a #surveillance LoJack for your wrist. Why should parole officers have all the fun? With the new Meta wrist band, they can track and profile your movements--providing terrabytes of data you paid for...but they get to exploit!

27.07.2025 05:08 β€” πŸ‘ 30    πŸ” 6    πŸ’¬ 3    πŸ“Œ 2

The police insist they need astronomical sums of money and complete immunity from any harm they cause in order to be ready to protect us and then half the time they just decide they’d prefer not to?

26.07.2025 22:43 β€” πŸ‘ 3906    πŸ” 1151    πŸ’¬ 130    πŸ“Œ 32
Post image

JUST IN: A federal judge has blocked the cancelation of $175 million in National Endowment for the Humanities grants, mass terminated by DOGE in April. She says the effort was transparent viewpoint discrimination in violation of the First Amendment.

26.07.2025 01:21 β€” πŸ‘ 4829    πŸ” 1330    πŸ’¬ 55    πŸ“Œ 72

BREAKING: Tesla launches human-driven car service for employees. /yawn

26.07.2025 02:26 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Microsoft’s AI CEO thinks Copilot will age and β€˜have a room that it lives in’ Copilot Appearance is live now

You can tell these folks live in a world where no one is allowed to tell them how ridiculous they sound.

25.07.2025 20:30 β€” πŸ‘ 125    πŸ” 33    πŸ’¬ 9    πŸ“Œ 11

Uber has been in business for 15 years. This is important safety feature is just being "piloted" now.

23.07.2025 21:59 β€” πŸ‘ 4    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0
Post image

This.

23.07.2025 09:37 β€” πŸ‘ 11    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0

@michaelzimmer is following 20 prominent accounts