rohan

6'3 for no reason

[rohan @roheeezy]

After 2 weeks of multiple health screens and asking everyone to quarantine, I surprised my closest inner circle with a trip to a private island where we could pretend things were normal just for a brief moment in time

[sugamummy 🧚🏽‍♀️ @ceraliza]

A guy I know lost both parents to a drunk driver. He got custody of his 3 siblings and had to drop out of uni to work and take care of them.

He used to joke a lot, always outside, always laughing. After it happened, he barely talked. Just always looked tired.

If this law had been in place it would have eased his burden a bit.

[Nav Toor @heynavtoor]

🚨SHOCKING: Apple just proved that AI models cannot do math. Not advanced math. Grade school math. The kind a 10-year-old solves.

And the way they proved it is devastating.

Apple researchers took the most popular math benchmark in AI — GSM8K, a set of grade-school math problems — and made one change. They swapped the numbers. Same problem. Same logic. Same steps. Different numbers.

Every model's performance dropped. Every single one. 25 state-of-the-art models tested.

But that wasn't the real experiment.

The real experiment broke everything.

They added one sentence to a math problem. One sentence that is completely irrelevant to the answer. It has nothing to do with the math. A human would read it and ignore it instantly.

Here's the actual example from the paper:

"Oliver picks 44 kiwis on Friday. Then he picks 58 kiwis on Saturday. On Sunday, he picks double the number of kiwis he did on Friday, but five of them were a bit smaller than average. How many kiwis does Oliver have?"

The correct answer is 190. The size of the kiwis has nothing to do with the count.

A 10-year-old would ignore "five of them were a bit smaller" because it's obviously irrelevant. It doesn't change how many kiwis there are.

But o1-mini, OpenAI's reasoning model, subtracted 5. It got 185.

Llama did the same thing. Subtracted 5. Got 185.

They didn't reason through the problem. They saw the number 5, saw a sentence that sounded like it mattered, and blindly turned it into a subtraction.

The models do not understand what subtraction means. They see a pattern that looks like subtraction and apply it. That is all.

Apple tested this across all models. They call the dataset "GSM-NoOp" — as in, the added clause is a no-operation. It does nothing. It changes nothing.

The results are catastrophic.

Phi-3-mini dropped over 65%. More than half of its "math ability" vanished from one irrelevant sentence.

GPT-4o dropped from 94.9% to 63.1%.

o1-mini dropped from 94.5% to 66.0%.

o1-preview, OpenAI's most advanced reasoning model at the time, dropped from 92.7% to 77.4%.

Even giving the models 8 examples of the exact same question beforehand, with the correct solution shown each time, barely helped. The models still fell for the irrelevant clause.

This means it's not a prompting problem. It's not a context problem. It's structural.

The Apple researchers also found that models convert words into math operations without understanding what those words mean. They see the word "discount" and multiply. They see a number near the word "smaller" and subtract. Regardless of whether it makes any sense.

The paper's exact words: "current LLMs are not capable of genuine logical reasoning; instead, they attempt to replicate the reasoning steps observed in their training data."

And: "LLMs likely perform a form of probabilistic pattern-matching and searching to find closest seen data during training without proper understanding of concepts."

They also tested what happens when you increase the number of steps in a problem. Performance didn't just decrease. The rate of decrease accelerated. Adding two extra clauses to a problem dropped Gemma2-9b from 84.4% to 41.8%. Phi-3.5-mini from 87.6% to 44.8%. The more thinking required, the more the models collapse.

A real reasoner would slow down and work through it. These models don't slow down. They pattern-match. And when the pattern becomes complex enough, they crash.

This paper was published at ICLR 2025, one of the most prestigious AI conferences in the world.

You are using AI to help you make financial decisions. To check legal documents. To solve problems at work. To help your children with homework. And Apple just proved that the AI is not thinking about any of it. It is pattern matching. And the moment something unexpected shows up in your question, it breaks. It does not tell you it broke. It just quietly gives you the wrong answer with full confidence.

[Tyrese Haliburton @Hali]

Alex Pretti was murdered.

[IcyVert @IcyVert]

If my All Pro TE blew his Achilles and then I see this 3 minutes later I’d probably stop watching football

[Poe's Law, Esq: Poe's Lawyer @dyingscribe]

Calling a death threat gay is hilarious

[diplo @diplo]

I was 20 when I first came to India with nothing but a restless mind and an old Enfield I bought from a friend in Delhi who taught me to ride in one dusty afternoon. He took my money, flew back to Florida, and left me with one rule: don’t hit a cow, and only ride between 2–6 a.m. if you want to survive the heat and smog. Somehow, that became a philosophy for everything that followed.

I crossed the country like a kid inside a dream — Calcutta to Delhi to Rishikesh — sleeping on the bike when I had to, chasing chai stalls to stay awake, tossing the bike on trains when I could afford it. I swam in the Ganges, did yoga with elders who moved like water, bought vinyl in back-alley shops, fell in love the way only your twenties let you, and wrote long confusing emails to my mom from glowing village internet cafés.

In Gujarat I stopped long enough to help with earthquake relief, eat thalis in strangers’ homes, and learn “Kem Cho” and “Majama.” India didn’t just teach me independence — it cracked me open creatively. It showed me how improvisation is its own kind of discipline, how getting lost is a form of education.

I never imagined I’d be invited back years later to collaborate with artists I once watched on café computers — working with actors like SRK, making videos like “Lean On” that crossed billions of views, nearly dying during spiritual side quests in Leh and Varanasi, falling for Bollywood sweethearts, and still believing every strange turn meant something.

Twenty-five years later I returned to these roads, riding nine hours a day across the Himalayas on a much newer Enfield. And then — perfectly — I ended up performing at a massive Enfield festival in Goa and celebrating afterward in a motorcycle garage, as if time folded back on itself.

Two decades have changed India and me both. But every time I come back, I feel the same truth: growth happens when you surrender to the unknown, when the road teaches you more than any classroom could.

India was my beginning. And somehow, it still is.

[Aidan Kohn-Murphy @AidanKohnMurphy]

however bad you’re imagining this essay to be, it’s sooo much worse. cannot believe a college student wrong this. 0/25 seems somehow generous lmao

[Ahmed/The Ears/IG: BigBizTheGod 🇸🇴 @big_business_]

Kenyon Martin and Nick Young have a very heated discussion on Gil’s Arena podcast 😬😬

Nick Young: Draymond had a top 5 point guard and won, you had a top 5 point guard carry you to the NBA Finals and you lost maybe if you played your role instead of scoring you would have a ring

KM: I played with Jason Kidd for 3 years I did my job

NY: They got rid of you so obviously you didn’t

[dakota @PowerOfDakota]

oh he was GAY gay

[𝘖𝘯𝘺𝘹𝘏𝘰𝘰𝘱𝘴 @OnyxHoops]

What in the actual fuck am I watching?

[Jesuit for X-Men @GracePersephone]

Star Wars-ass picture.

[rohan @roheeezy]

@parismartineau @ConsumerReports Did you guys test Kirkland (Costco) protein powder?

[The Kevin Harlan Effect @KevHarlanEffect]

Please look at Kyle Shanahan’s face after the Mac Jones injury 💀

[Blossom @blossom102122]

I am trying not to post hinge screenshots but I am just too hilarious

[rohan @roheeezy]

@noor_supernova7 .

[DRUSKI @druski]

That Guy who is just Proud to be AMERICAN🇺🇸

[Mel @Villgecrazylady]

Do you want to see what Zionist privilege looks like? Look no further than this! A juxtaposition of the criminal justice systems in Israel and America when experienced by each others citizens:

First up, the American: Mohammed Ibrahim

In February of this year, 15 year old Mohammed Ibrahim, was arrested by Israel while visiting family in the West Bank, on charges of “throwing rocks.”

He was blindfolded, handcuffed and thrown in a maximum security prison where he has been ever since awaiting trial.

Mohammed has lost 25 pounds and currently has scabies, an incredibly infectious and often very painful skin infection. His family’s lawyer has only been allowed to see him twice.

Now the Israeli: Tom Alexandrovich

Tom Alexandrovich was attending a conference in Las Vegas earlier this month, as head of the Israel National Cyber Directorate. According to Las Vegas Police, Tom used his computer to try and lure a child to an facility in order to have sex with them, except Tom was actually in contact with a law enforcement agent and was swiftly arrested and charged by the Henderson County PD.

So is Tom suffering a similar fate as Mohammed, except here in an American jail? Of course NOT!

Because it turns out Tom works for Benjamin Netanyahu so despite being charged with sex crimes against children, Tom was released from jail the next day and allowed to fly home to Israel.

See how that works?

If you’re an American teenager charged with “throwing rocks” in the West Bank, you’re thrown in a dungeon and left to rot.

But if you’re a grown ass Israeli man and you try to lure an underage American girl to a hotel room to have sex with you, you spend a few hours in jail and then get to fly home to Israel the next day, no questions asked.

The difference really couldn’t be more stark.