日韩精品久久一区二区三区_亚洲色图p_亚洲综合在线最大成人_国产中出在线观看_日韩免费_亚洲综合在线一区

Global EditionASIA 中文雙語(yǔ)Fran?ais
World
Home / World / Americas

Inner workings of AI an enigma even to its creators

Updated: 2025-05-14 10:12
Share
Share - WeChat

NEW YORK — Even the greatest human minds building generative artificial intelligence that is poised to change the world admit that they do not comprehend how digital minds think.

"People outside the field are often surprised and alarmed to learn that we do not understand how our own AI creations work," Dario Amodei, co-founder of AI startup Anthropic, wrote in an essay posted online last month.

"This lack of understanding is essentially unprecedented in the history of technology."

Unlike traditional software programs that follow preordained paths of logic dictated by programmers, generative AI models are trained to find their own way to success, once prompted.

In a recent podcast, Chris Olah, who was part of ChatGPT-maker OpenAI before joining Anthropic, described generative AI as "scaffolding" on which circuits grow.

Olah is considered an authority in so-called mechanistic interpretability, a method of reverse engineering AI models to figure out how they work.

This science, born about a decade ago, seeks to determine exactly how AI gets from a query to an answer.

"Grasping the entirety of a large language model is an incredibly ambitious task," said Neel Nanda, a senior research scientist at the Google DeepMind AI lab.

It was "somewhat analogous to trying to fully understand the human brain", Nanda told Agence France-Presse, noting neuroscientists are yet to succeed on that front.

Delving into digital minds to understand their inner workings has gone from a little-known field just a few years ago to being a hot area of academic study.

"Students are very much attracted to it because they perceive the impact that it can have," said Boston University computer science professor Mark Crovella.

The area of study is also gaining traction because of its potential to make generative AI even more powerful, and because peering into digital brains can be intellectually exciting, Crovella added.

Mechanistic interpretability involves studying not just results served up by generative AI but scrutinizing calculations performed while the technology mulls queries, he said.

"You could look into the model ... observe the computations that are being performed and try to understand those."

Better understanding

Startup Goodfire uses AI software capable of representing data in the form of reasoning steps to better understand generative AI processing and correct errors.

The tool is also intended to prevent generative AI models from being used maliciously or from deciding on their own to deceive humans about what they are up to.

"It does feel like a race against time to get there before we implement extremely intelligent AI models into the world with no understanding of how they work," said Goodfire Chief Executive Eric Ho.

Amodei of Anthropic said in his essay that recent progress has made him optimistic that the key to fully deciphering AI will be found within two years.

Crovella of Boston University said researchers can already access representations of every digital neuron in AI brains.

"Unlike the human brain, we actually have the equivalent of every neuron instrumented inside these models," he said. "Everything that happens inside the model is fully known to us. It's a question of discovering the right way to interrogate that."

Harnessing the inner workings of generative AI minds could clear the way for its adoption in areas where tiny errors can have dramatic consequences, such as national security, Amodei said.

"Powerful AI will shape humanity's destiny," Amodei wrote.

"We deserve to understand our own creations before they radically transform our economy, our lives, and our future."

Agencies Via Xinhua

Most Viewed in 24 Hours
Top
BACK TO THE TOP
English
Copyright 1995 - . All rights reserved. The content (including but not limited to text, photo, multimedia information, etc) published in this site belongs to China Daily Information Co (CDIC). Without written authorization from CDIC, such content shall not be republished or used in any form. Note: Browsers with 1024*768 or higher resolution are suggested for this site.
License for publishing multimedia online 0108263

Registration Number: 130349
FOLLOW US
主站蜘蛛池模板: 亚洲精品午夜视频 | 久久道| 国产欧美曰韩一区二区三区 | 免费a一级毛片在线播放 | 日韩欧美一区二区三区视频 | 亚洲永久| 97久久超碰 | 美美女高清毛片视频免费观看 | 色偷偷888欧美精品久久久 | 免费午夜理论不卡 | 久久久久亚洲精品中文字幕 | 日日操天天操夜夜操 | 狠狠干伊人网 | 精品视频在线播放 | 国产91在线观看 | 日本青草视频 | 手机看片日韩欧美 | 日本www视频在线观看 | 亚洲午夜成激人情在线影院 | 精品一区二区日本高清 | 俄罗斯色妞18av | 欧美va亚洲 | 国产精品久久久久久中文字 | 中文字幕亚洲一区二区三区 | 欧美三级电影在线观看 | 欧美一区二区三区视频 | 天天色天天 | 91欧美激情一区二区三区成人 | 91av视频在线免费观看 | 国产精品美女久久久久久久网站 | 精品视频在线观看 | 久久久久99 | 欧美1区| 天堂中文资源网 | 九九久久久 | 亚洲一区二区三区免费在线观看 | 久久久久久久成人 | 久草久热 | 久色视频在线观看 | 久久色亚洲 | 久草福利免费 |