


Researchers lift the lid on how reasoning models actually “think”
They plan sentences far in advance. They also bullshit themselves when reasoning out loud
As all scribblers of doggerel know, rhymes must be paired up before you start a new line. Otherwise you may write yourself into a dead end with an ill-placed “purple” or “orange”. It is an insight that is shared by artificial intelligence (AI), new research shows. When Claude, a large language model (LLM), is asked to write a rhyming couplet, it begins thinking of the second part of the rhyme as soon as the first word is written. Give it the first line “he saw a carrot and had to grab it”, and the AI begins contemplating rabbits at once, writing the next sentence to end at the appropriate rhyme.
Explore more

How Daylight Saving Time affects your sleep and diet
This annual time shift has long-lasting effects on health

Motors in the wheels take EVs further
Simpler to build, lighter and extra range

What does space miso taste like?
It should make the diets of astronauts more interesting
Mitochondria transplants could cure diseases and lengthen lives
A technique that may create a new field of medicine
Is red meat unhealthy?
Overdoing it could give you heart disease or cancer
Can Musk put people on Mars?
Whether successful or not, his attempt to do so will reshape America’s space programme