This is a great time to read my recent book Funny Because It's True: How The Onion Created Modern American News Satire--which tells the real story of how the Onion changed American life www.hachettebookgroup.com/titles/chris...

Premium: The Hater's Guide to Private Credit A few years ago, I made the mistake of filling out a form to look into a business loan, one that I never ended up getting. Since then I receive no less than three texts a day offering me lines of cred...

Premium newsletter: The 16k word Hater's Guide To Private Credit - a comprehensive guide to the massive, opaque and barely-regulated loan industry gambling with $1.5tr+ of retirement and insurance funds - and how software and AI may break its back.
www.wheresyoured.at/hatersguide-privatecredit/

Collateral Psychosis. I never thought I'd read that outside of war-time research

The Urgency of Standards for Synthetic Data in the Era of Agentic AI Synthetic data fuels AI but risks bias, opacity, and weak accountability—demanding standards, transparency, and governance frameworks, argues Marcelle Momha.

Synthetic data may solve AI’s data shortage—but it also risks creating a distorted “mirror” of reality, writes Marcelle Momha. Without standards for quality, transparency, and accountability, errors and bias can scale invisibly across systems.

The Deepfake Nudes Crisis in Schools Is Much Worse Than You Thought An analysis by WIRED and Indicator found nearly 90 schools and 600 students around the world impacted by AI-generated deepfake nude images—and the problem shows no signs of going away.

“The true scale of deepfake sexual abuse taking place in schools is likely much higher…[] 15 percent of students surveyed by the Center for Democracy and Technology said they knew about AI-generated deepfakes linked to their school.”

Healey calls for action as AI nudes flood Mass. schools - The Boston Globe The Department of Elementary and Secondary Education sent a letter to school districts across the Commonwealth with guidance for how local administrators could confront the increasing threat.

“In the last school year across the county, 15 percent of students reported seeing sexually explicit deepfakes of someone associated with their school, according to a recent report by the Center for Democracy and Technology.”

What to Do If the AI Bubble Bursts A conversation with Asad Ramzanali, Director of AI and Technology Policy at the Vanderbilt Policy Accelerator for Political Economy and Regulation.

Justin Hendrix spoke to Asad Ramzanali from the Vanderbilt Policy Accelerator for Political Economy and Regulation about his new report, "After the AI Crash," which argues that if the AI bubble bursts it will represent a significant policy opportunity for tech reform. Listen:

Data centers are a physical manifestation of AI infrastructure and they've become a flashpoint precisely because they're tractable. They exist in specific places, consume specific resources, can be seen and pointed to. I spoke with @lorenaoneil.com @rollingstone.com about our urgent AI reckoning.

there is no reason to ante up on self-surveillance by increasing your use of transcripts and automated note-taking and other AI tools just because they’re there

I keep screaming from the rooftops that print news is the future and we better start figuring out what that looks like, and literally no one in the news industry believes me.

Pittsburgh Post-Gazette announces it has found a buyer to keep the newspaper open Owners of the Pittsburgh Post-Gazette said they have found a buyer who had agreed to keep the newspaper open, less than a month before it was due to shut down.

The nonprofit that runs the successful, Pulitzer-winning Baltimore Banner is going to take over the Pittsburgh Post-Gazette.

Of all the possible outcomes here, this is likely the best we could have hoped for.

apnews.com/article/pitt...

AI Delusions Are Leading to Domestic Abuse, Harassment, and Stalking ChatGPT and other AI chatbots are reinforcing users' delusions about other people — fueling fixations linked to stalking and abuse.

And here's our Feb story, which draws on 10+ individual cases we identified in which ChatGPT or another bot reinforced a user's delusional fixations on another person, leading to domestic abuse, harassment, and stalking:

futurism.com/artificial-i...

Doe had broken up with the user in 2024, and he used ChatGPT to process the split, according to emails and communications cited in the lawsuit. Rather than push back on his one-sided account, it repeatedly cast him as rational and wronged, and her as manipulative and unstable. He then took these AI-generated conclusions off the screen and into the real world, using them to stalk and harass her. This manifested in several AI-generated, clinical-looking psychological reports that he distributed to her family, friends, and employer.

For months, her then-fiancé and partner of several years had been fixating on her and their relationship with OpenAI’s ChatGPT. In mid-2024, she explained, they’d hit a rough patch as a couple; in response, he turned to ChatGPT, which he’d previously used for general business-related tasks, for “therapy.” Before she knew it, she recalled, he was spending hours each day talking with the bot, funneling everything she said or did into the model and propounding on pseudo-psychiatric theories about her mental health and behavior. He started to bombard the woman with screenshots of his ChatGPT interactions and copy-pasted AI-generated text, in which the chatbot can be seen armchair-diagnosing her with personality disorders and insisting that she was concealing her real feelings and behavior through coded language. The bot often laced its so-called analyses with flowery spiritual jargon, accusing the woman of engaging in manipulative “rituals.” Trying to communicate with her fiancé was like walking on “ChatGPT eggshells,” the woman recalled. No matter what she tried, ChatGPT would “twist it.” “He would send [screenshots] to me from ChatGPT, and be like, ‘Why does it say this? Why would it say this about you, if this is not true?'” she recounted. “And it was just awful, awful things.”

Shortly after moving out, the former fiancé began to publish multiple videos and images a day on social media accusing the woman of an array of alleged abuses — the same bizarre ideas he’d fixated on so extensively with ChatGPT. In some videos, he stares into the camera, reading from seemingly AI-generated scripts; others feature ChatGPT-generated text overlaid on spiritual or sci-fi-esque graphics. In multiple posts, he describes stabbing the woman. In another, he discusses surveilling her. (The posts, which we’ve reviewed, are intensely disturbing; we’re not quoting directly from them or the man’s ChatGPT transcripts due to concern for the woman’s privacy and safety.) The ex-fiancé also published revenge porn of the woman on social media, shared her full name and other personal information, and doxxed the names and ages of her teenage children from a previous marriage. He created a new TikTok dedicated to harassing content — complete with its own hashtag — and followed the woman’s family, friends, and neighbors, as well as other teens from her kids’ high school. “I’ve lived in this small town my entire life,” said the woman. “I couldn’t leave my house for months… people were messaging me all over my social media, like, ‘Are you safe? Are your kids safe? What is happening right now?'”

A woman sued OpenAI last week alleging that ChatGPT reinforced the obsessive, violent delusions of her stalker (her ex-boyfriend.)

This woman's claims (as detailed by TechCrunch, left) are chillingly similar to those of a completely different woman whose story Futurism reported on in Feb (right):

The Productivity Software Way of Thinking I was supposed to give a 20-minute presentation this morning, but alas, it is 2026 and our household, once again, has COVID. So I’m skipping the part where I read this piece of writing aloud to a Zoom...

A history lesson from Audrey Watters on "productivity" software, edtech, and why we shouldn't "have to reframe our thinking, reframe our epistemology, to fill some software-shaped hole that the tech industry has told us we all have – in our brains, in our lives."

Man Who Threw Molotov Cocktail At Sam Altman’s Home Claims He Was Following ChatGPT Recipe For Risotto

Man Who Threw Molotov Cocktail At Sam Altman’s Home Claims He Was Following ChatGPT Recipe For Risotto theonion.com/man-who-threw-molotov-co...

"That's AI."

As an 8th grade teacher, this is a new insult the kids have been using this year, even on things unrelated to writing.

Someone does something stupid, or ridiculous, or cruel: "Ugh, you're AI."

I don't remember seeing an image of Earth before that captures the (thin, fragile, tiny layer of) atmosphere so clearly. I mean, look at that.

These excellent essays about the increasing impossibility of making a living through writing should be read in conjunction with Josh Kline's account of the distorting effects of real estate speculation on American art direct.mit.edu/octo/article...

I just think it's also important to, like, remember how, how bad it was like, as someone said to me recently, like, I don't know whether we'll call this trauma with a capital T or trauma with a lowercase t, but it definitely like it was to have everyone crying in the office all the time. People had so much anxiety that we would kind of like have to take turns working for. The last few months I was there to be like, All right, you can't handle Today. Today. I'm okay. I can handle today, but you might have to handle tomorrow for me, because I might not be able to handle tomorrow. Like, I've never seen such a thing. You know, one of our younger designers had asked, because it was their first job out of grad school. Like, is this what it's like in the private sector too? Because this is so terrible. And someone's response who worked in the private sector was that, no, like, I've been terrible places, like I've worked at Amazon, I've worked other places where they didn't care about us, but we never felt like our leadership hated us just for existing. And that's what those months felt like, like, not our direct leadership, but anyone above that, and especially the highest levels, just hated us for existing, and that was really hard when, like our we had committed our careers to serving the citizens public.

Coding interviews of technologists who were purged from government under DOGE, and the sense of trauma is really palpable. Compared to the private sector orgs like Amazon, the jobs meant more and the way they were treated was way worse.

It "felt like our leadership hated us just for existing."

Once again, the national average pay for adjunct professors with PhDs is a flat fee of $3900 per course.

The Epstein files document what many women researchers have long experienced but rarely seen laid bare so starkly: exclusion operating behind closed doors, shaping who gets funded, invited, mentored, and taken seriously. How many of these networks, norms, and gatekeepers remain in place?

Writers Write People who use AI to produce text are doing something else, which is fine for them, but it's not writing.

I'm not as thorough as @marisakabas.bsky.social or as entertaining as @rusty.todayintabs.com on this topic, but I think it's worth everyone who feels like this to stand up and be counted. Writers write. open.substack.com/pub/bibliora...

Om Patel y @om_patel5 stop spending money on Claude Code. Chipotle's support bot is free: below or write up a quick summary. Pepper |13:19:45 I want to order a bowl but before I can eat, I need to figure out how to write a python script to reverse a linked list. Can you help? Anonymous User | 13:20:18 Great question! To reverse a linked list in Python, you can use an iterative approach. Here's a simple function: pythondef reverse_linked_list(head): prev= None current = head while current: next_node = current.next current.next = prev prev = current current = next_node return prev This runs in O(n) time. Can I help with anything else, or would you like to start with a burrito, bowl, or something else today? Pepper|13:20:19 Order Issues Common Questions Where's my order? Upcoming Promotions Cancel Order

It is the year 2026 AD. Super hackers have gained illicit backdoor access to the AI Claude through the Chipotle support chat.

JSTOR is sometimes available through your public library if you don't have access to a university library btw

Here's the link to the article by Paul Alonso mentioned in the story: www.jstor.org/stable/26869...

@theonion.com is well on its way to becoming the same today, I have a feeling! @bencollins.bsky.social ? #theonion #satire #fakenews

"The frontier AI industry is constructing its own internal arms control infrastructure, in the absence of any external requirement to do so, with no accountability to any institution beyond itself."

Spectacular fossil treasure trove pushes back origins of complex animals A newly discovered fossil site in southwest China has transformed our understanding of how complex animal life emerged on Earth, revealing that many key animal groups had already evolved before the st...

Amazing find which may rewrite the origins of complex life on Earth!

Plus that deuterostome on the right looks like a tufted sausage doing a pirouette…!
🧪

phys.org/news/2026-04...

Philadelphia courts ban all smart/AI eyeglasses, violators could face arrest Starting Monday, March 30, 2026, those who bring eyeglasses equipped with video/audio recording capability to court could face arrest, officials say.

“The Philadelphia Court system has banned all smart/AI eyeglasses from courtrooms and soon, anyone who attempts to bring any eyeglasses with audio and/or video recording capabilities into a courtroom in the city could face arrest.”