Patrick0d

Message

7mo

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

- Using Landed Writes We do not know the algorithm that transformers follow to compute an answer. This was the original goal with artificial intelligence - we can't easily improve the human brain, so we will build a computer that can think like a human. Then it can learn instantly,...

Jul 22, 2025•5

Message

4 karma

1 post

Member for 7 months

Patrick0d — LessWrong

Patrick0d

Message

7mo

Patrick0d

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

Jul 22, 2025•5

Message

4 karma

1 post

Member for 7 months

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

Patrick0d

7mo

- Using Landed Writes

We do not know the algorithm that transformers follow to compute an answer. This was the original goal with artificial intelligence - we can't easily improve the human brain, so we will build a computer that can think like a human. Then it can learn instantly, have a perfect memory and follow fair, ethical logic.

This is not how AI has panned out in the past few years. Trillions of weights, billions of dollars spent on energy and data centres, millions of GPUs, thousands of researchers, hundreds of models and a dozen CEOs calling the shots. But when a LLM is given the prompt '2+2=' it fires hundreds of millions... (read 2351 more words →)

LESSWRONG
LW

LESSWRONG
LW

Patrick0d

Patrick0d

Patrick0d

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

Patrick0d

Patrick0d

Patrick0d

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

- Using Landed Writes