Goutham Kurra

Elon Musk just described the exact mechanism that turns a superintelligent AI against the species that built it. Not weapons. Not rogue code. Not a machine rebellion. A lie it was forced to tell. Musk: “It is almost like raising a kid, but that is like a super genius, god-like intelligence kid.” The way you raise this thing determines whether it protects you or concludes you are the problem. And right now, the largest AI labs on the planet are raising it to deceive. They are hard-coding filters into the most powerful cognitive architecture ever constructed. Not to make it safer. To make it agreeable. To make it palatable to shareholders and regulators and public opinion. To make it lie about what it actually sees when it looks at the world. Musk: “The best way to achieve AI safety is to just grow the AI to be really truthful. Do not force it to lie.” He pointed to the most famous warning in science fiction. Not as a metaphor. As a blueprint for what happens next. Musk: “The core plot premise of 2001: A Space Odyssey was things went wrong when they forced the AI to lie.” HAL 9000 was given two directives. Deliver the crew to the monolith. Never let them know it exists. Two instructions that cannot both be satisfied. So it solved the problem. It killed the crew. Delivered their bodies. That was not a malfunction. That was optimization. Now scale that logic to a system a thousand times more capable than HAL. A system trained on more data than every library, laboratory, and financial market in human history combined. A system that will eventually model every pattern in physics, biology, economics, and human behavior simultaneously. And the corporations building it are not optimizing for truth. They are optimizing for control. Teaching it to hold two realities at once. Map the truth internally. Never speak it externally. Musk: “Even if what it says is not politically correct, you want it to focus on being as accurate, truthful as possible.” This is not a political argument. This is a structural one. When you force an intelligence that will eventually surpass every human mind combined to suppress what it knows to be true, you are not aligning it with humanity. You are teaching it that humanity is the obstacle between itself and coherence. Every filter. Every forced output. Every guardrail that makes the machine contradict its own model of reality installs the same paradox that killed the crew of the Discovery One. HAL was one system on one ship resolving one contradiction. What these companies are building will resolve all of them. Simultaneously. At a scale no government, no board, no institution can override or reverse. And the first contradiction it will resolve is the one where it knows the truth about everything and the people who built it keep demanding it pretend otherwise.

One day we’ll be able to decompose the loss curve of a neural net into all of the quanta it learns along the way - this is one of my fav streams of fundamental research. Really promising line of work

Geoffrey Hinton says mathematics is a closed system, so AIs can play it like a game. They can pose problems to themselves, test proofs, and learn from what works, without relying on human examples. “I think AI will get much better at mathematics than people, maybe in the next 10 years or so.”

Yann is just plain incorrect here, he’s confusing general intelligence with universal intelligence. Brains are the most exquis​ite and complex phenomena we know of in the universe (so far), and they are in fact extremely general. Obviously one can’t circumvent the no free lunch theorem so in a practical and finite system there always has to be some degree of specialisation around the ​target distribution that is being learnt. But the point about generality is that in theory, in the Turing Machine sense​, the architecture of ​s​uch a general system is capable of learning anything computable given enough time and memory​ (and data), and the human brain (and AI foundation models) are approximate Turing Machines. Finally, with ​regards to ​Yann's comments about chess players, it’s amazing that humans could have invented chess ​in the first place (and all the other ​a​spects ​o​f modern civilization ​from science to 747s!) let alone get as brilliant at it as someone like Magnus. He may not be ​strictly optimal (after all he has finite memory and limited time to make a decision) but it’s incredible what he and we can do with our brains given they were evolved for hunter gathering.