Orange & Dirty 🇺🇲⬆️ 👨‍🔧

@heynavtoor @grok aced it!

🚨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.

HOT TAKE: IF BUSINESSES ONLY HAVE TO PAY TAXES ON PROFIT, NOT REVENUE, THEN I SHOULD ONLY HAVE TO PAY TAXES AFTER I'VE PAID ALL MY BILLS AND RENT.

@Not__Nicola 100%

@AndrewYang @joinnoblemobile Dang, not been on but this is hilarious!

Please, put your phone down! @joinnoblemobile

Just started listening to the new book @AndrewYang and loving it! Definitely miss your voice, stories, takes, and humor! #yanggang

The results from Germany's 3-year UBI experiment are out! 122 people got €1200/mo for 3 years. All were age 21-40 and employed with €1100-€2600/mo pay. They were happier, healthier, saved more, gave more, enjoyed more social time and DID NOT WORK LESS than the control group.

@Not__Nicola At least she told you who she is! Just immature

My name is Nicola . So when I introduce myself if the person questions it or struggles with it , I always say “ yeah like Nicola Tesla the scientist” and the usual response is oh that’s cool . This week at work this girl said “ew” in response . 😂 so weird .

He argued against lockdowns because he is not a fucking idiot Damn the news media is dishonest

@dbodybalancer I remember your little movie you were in! Lol

@YoshidaG 😉😋 me too, me too lol

MAGA RED ❤️😘💋 Victory Red. #MAGA #MAHA #Trump

@dbodybalancer I could totally visualize you acting that out! Lol

@YoshidaG Oh well i do declare! You are too kind 😌 Thank yeeew sir

@dbodybalancer Agree! 100%

I believe what we’re witnessing is a mass hysteria, evidenced by the meltdowns coming from the left, and I really blame the whole corrupt “news” media/ propaganda arm of the deep state that’s been controlled by the Dems. I want to see some serious retribution for it.

@T4YPodcast Craaaaazzzzyyyyyy

Another lab leak... Anybody heard from Anthony Fauci?

@scottsantens @DrEricDing Agree to disagree

@YoshidaG @DrEricDing Rogan was having terrible discussions with terrible people in the middle of a pandemic that ended up discouraging people from getting vaccines and wearing masks. They were not "the right" discussions to uplift nonsense about ivermectin.

Hear me out—Dems did once “have their own Joe Rogan”—his name is Joe Rogan, who is inherently not MAGA. He was a fan of Obama, Bernie Sanders, Andrew Yang, universal healthcare, taxing the rich, and disliked Trump. And Rogan reaches men that Dems need.

@scottsantens @DrEricDing Agree it was the pandemic and the concerted effort to censor him from having important discussions which many have proven to have been the right discussions to be having. That is when the left turned on him!

@DrEricDing I think the pandemic broke Rogan, as it did many others. He was not MAGA but he sure seems that way now, and I would not blame anyone for pushing him away. I think he just went in that direction, possibly due to audience capture and just his choice of guests to influence him.

@BrandonBukas Congrats!

She said yes :)

@HeidiBriones As long as they know how to work it!

It's true.

After years of preparation, we're excited to introduce the Forward Party to Nevada! Huge thanks to our volunteers, allies, mentors, and everyone who believed in us. 🙏⬆️ Article 🔗: reviewjournal.com/news/politics-… #ForwardNV #RankedChoiceVoting #Nevada @fwd_nv @fwd_party @AndrewYang

Hey @Fwd_Party I asked ChatGPT a question, got a cool answer.

I was going to cancel my Twitter subscription because... Who cares? After seeing this from @elonmusk, I have decided to keep it and will commit to a $10k ad buy, the largest I have ever done. We need to support free speech and empower those who support it. GFY, Bob.👍