Pragmatic Thinking retweeted
🚨 MIT just humiliated every major AI lab and nobody’s talking about it.
They built a new benchmark called WorldTest to see if AI actually understands the world… and the results are brutal.
Even the biggest models Claude, Gemini 2.5 Pro, OpenAI o3 got crushed by humans.
Here’s what makes it different:
WorldTest doesn’t check how well an AI predicts the next word or frame.
It measures if it can build an internal model of reality and use that to handle new situations.
They built AutumnBench 43 interactive worlds, 129 tasks where AIs must:
• Predict hidden parts of the world (masked-frame prediction)
• Plan multi-step actions to reach goals
• Detect when the rules of the environment suddenly change
Then they tested 517 humans vs the top models.
Humans dominated every category.
Even massive compute scaling barely helped.
The takeaway is wild:
Today’s AIs don’t understand environments they just pattern-match inside them. They don’t explore, revise beliefs, or experiment like humans do.
WorldTest might be the first benchmark that actually measures understanding, not memorization. And the gap it reveals isn’t small it’s the next grand challenge in AI cognition.
(Comment “Send” and I’ll DM you the paper 👇)
Pragmatic Thinking retweeted
Really happy to share our new paper on using AlphaEvolve for mathematical exploration at scale, written with Javier Gómez-Serrano, Terence Tao, and @GoogleDeepMind's Bogdan Georgiev. We tested it on 67 problems and documented all our successes and failures. 🧵
Pragmatic Thinking retweeted
Can AI invent new math?
A new paper from DeepMind and renowned mathematician Terence Tao shows how.
Using AlphaEvolve, the team merges LLM-generated ideas with automated evaluation to propose, test, and refine mathematical algorithms.
In tests on 67 problems across analysis, geometry, and number theory, AlphaEvolve not only rediscovered known results but often improved upon them—even generalizing finite cases into universal formulas.
Paired with DeepThink and AlphaProof, it points toward a future where AI doesn’t just assist mathematicians—it collaborates with them in discovery.
Pragmatic Thinking retweeted
Two cents on AI getting International Math Olympiad (IMO) Gold, from a mathematician.
Background:
Last year, Google DeepMind (GDM) got Silver in IMO 2024.
This year, OpenAI solved problems P1-P5 for IMO 2025 (but not P6), and this performance corresponds to Gold. (1/10)
Pragmatic Thinking retweeted
We should all be very disturbed by the fact that basically everyone who wants to run for Congress is forced to pledge allegiance to Israel!!
Also, god bless @RepThomasMassie — you are an American hero! 🫡🇺🇸
Pragmatic Thinking retweeted
Two Jewish Israelis planted bombs reading “Revenge From Tulkarm” on empty buses, causing a major army escalation in the occupied West Bank. This is a typical Israeli false flag operation.
Pragmatic Thinking retweeted
Diana Magnay reporting that in November 2023 Hamas offered to return the bodies of the Bibas family after they were killed in an Israeli air strike, and Israel refused, "saying this was psychological warfare"
Pragmatic Thinking retweeted
Genocide apologists are trying to get the BBC to remove the documentary 'Gaza: How to Survive a Warzone' from iPlayer.
Here are some clips from the film (all the footage was filmed by two Palestinian cameramen in Gaza)
Pragmatic Thinking retweeted
Mayor Pete failed for four years to address the air traffic controller shortage and upgrade our outdated, World War II-era air traffic control system. In less than four weeks, we have already begun the process and are engaging the smartest minds in the entire world.
Here’s the truth: the FAA alone has a staggering 45,000 employees. Less than 400 were let go, and they were all probationary, meaning they had been hired less than a year ago. Zero air traffic controllers and critical safety personnel were let go.
Mayor Pete chose to use this amazing department—that is so critical to America’s success—as a slush fund for the green new scam and environmental justice nonsense. Not to mention that over 90% of the workforce under his leadership were working from home - including him. The building was empty!
When we finally get a full accounting of his mismanagement, I look forward to hearing from him.
In the meantime, I will not rest until I return the Department of Transportation and its incredible employees to its mission of efficiency and safety.
Pragmatic Thinking retweeted
The murder of journalists is a war crime. But for the first time in my memory, Israel targeted their family members as well.
Israel Killed Two-Thirds of All Journalists Slain in 2024, the Deadliest Year for Reporters democracynow.org/2025/2/14/h…
Pragmatic Thinking retweeted
The US government sent $2.7 TRILLION in Medicare & Medicaid money overseas to people who were NOT eligible to receive it.
That’s 8% of our national debt.
Medicare isn't going broke. The money is being stolen.
Pragmatic Thinking retweeted
JUST IN:
🇺🇲🇪🇺 US Vice President J.D. Vance:
"The greatest threat to Europe is not Russia or China, it is the threat from within against traditional European values"
Pragmatic Thinking retweeted
Einstein tried to warn the world about Zionism and Jewish terrorism, in April, 1948.
Pragmatic Thinking retweeted
President Harry S Truman expresses his frustration that zionists wanted to steal the whole of Palestine.
Pragmatic Thinking retweeted
Israel doesn’t need the ICJ to prove they have committed a genocide and are intent on ethnically cleansing the Palestinians…
Their government officials openly admit a brag about their crimes…🇮🇱🇵🇸
Pragmatic Thinking retweeted
The moment the Israeli occupation forces opened fire on a family while they were inspecting their home yesterday.
The Israeli soldiers killed the father next to his two sons.
Pragmatic Thinking retweeted
Israel 🇮🇱 not only occupies Palestine but ✡️ they Occupy USA entirely.
Americans are Noticing at massive levels never seen before and we don’t support forever wars for Greater Israel.
Pragmatic Thinking retweeted
A man performing during the Kendrick Lamar halftime concert at #SuperBowl LIX unfurled a Palestinian flag and was chased off stage and finally tackled and removed by security. #SBLIX #Palestine
Pragmatic Thinking retweeted
"Arabs are inferior to us. That's why we kick Palestinians and slap them. We train dogs so they will bite them strongly and tightly. That's why we shoot them. They're nothing"
—Tel-Aviv school principal, literally teaching kids to hate.























