AI’s understanding and reasoning skills can’t be assessed by current tests

“Sparks of artificial general intelligence,” “near-human levels of comprehension,” “top-tier reasoning capacities.” All of these phrases have been used to describe large language models, which drive generative AI chatbots like ChatGPT. Since that bot arrived on the scene in late 2022, it seems as if every new generative AI is the next, best iteration — not just producing humanlike content but also approaching near-human cognition (SN: 12/11/23). But what can we really say about any LLM’s ability to reason and understand?

In the AI community, there is no consensus on the definition of machine “intelligence,” nor on how to define the various cognitive capabilities often attributed to LLMs. Such

→ Continue reading at Science News

More from author

Related posts

Advertisment

Latest posts

Elon Musk beats $500 million severance lawsuit by fired Twitter workers | CNN Business

CNN  —  Elon Musk won dismissal of a lawsuit claiming he refused to pay at least $500 million...

New York University settles lawsuit over antisemitism for undisclosed amount | CNN Business

New York CNN  —  New York University has settled a federal lawsuit with students over antisemitism on campus for...

Breastfeeding should take a toll on bones. A brain hormone may protect them

Birthing and caring for a newborn can be hard on a mother’s bones. Estrogen, which helps regulate bone growth, drops precipitously after birth, and...