ChatGPT’s creators have attempted to get the system to explain itself. They found that while they had some success, they ran into some issues – including the fact that artificial intelligence may be using concepts that humans do not have named for, or understanding of. Researchers at OpenAI, which developed ChatGPT, used the most recent version of its model known as GPT-4 to try and explain the behaviour of GPT-2, an earlier version. It is an attempt to overcome the so-called black box problem with large language models such as GPT. While we have a relatively good understanding of what goes into and comes out of such systems, the actual work that goes on inside remains largely mysterious. That is not only a problem because it makes things difficult for researchers. It also means that there is little way of knowing what biases might be involved in the system, or if it is providing false information to people using it, since there is no way of knowing how it came to the conclusions it did. Engineers and scientists have aimed to resolve this problem with “interpretability research”, which seeks find ways to look inside the model itself and better understand what is going on. That has often required looking at the “neutrons” that make up such a model: just like in the human brain, an AI system is made up of a host of so-called neutrons that represent parts of the data it uses. Finding those is difficult, however, since humans have had to pick through the neurons and manually inspect them to find out what they represent. But some systems have hundreds of billions of parameters and so actually getting through them all with people is impossible. Now, researchers at OpenAI have looked to use GPT-4 to automate that process, in an attempt to more quickly pick through the behaviour. They did so by attempting to create an automated process that would allow the system to provide natural language explanations of the neuron’s behaviour – and apply that to another, earlier language model. That worked in three steps: looking at the neuron in GPT-2 and having GPT-4 try and explain it, then simulating what that neuron would, and finally scoring that explanation by comparing how the simulated activation worked with the real one. Most of those explanations went badly, and GPT-4 scored itself poorly. But researchers said that they hoped the experiment showed that it would be possible to use the AI technology to explain itself, with further work. The creators came up against a range of “limitations”, however, that mean the system as it exists now is not as good as humans at explaining the behaviour. Part of the problem may be that explaining how the system is working in normal language is impossible – because the system may be using individual concepts that humans cannot name. “We focused on short natural language explanations, but neurons may have very complex behavior that is impossible to describe succinctly,” the authors write. “For example, neurons could be highly polysemantic (representing many distinct concepts) or could represent single concepts that humans don’t understand or have words for.” It also runs into problems because it is focused on specifically what each neuron does individually, and not how that might affect things later on in the text. Similarly, it can explain specific behaviour but not what mechanism is producing that behaviour, and so might spot The system also uses a lot of computing power, the researchers note. Read More Google to unveil major new AI AI robots figure out how to play football in shambolic footage White House asks hackers to break ChatGPT White House reveals plan to ‘protect’ citizens from danger of AI DeepMind boss says human-level AI is just a few years away Regulator to probe use of artificial intelligence such as ChatGPT

Elon Musk's Twitter is now X. The rebrand, which was made official on Monday, has

Scientists have been left shocked and worried by a recent discovery made beneath the Thwaites Glacier in Antarctica, otherwise known as the 'doomsday glacier.' The huge amount of ice has been destablised and has been reduced by nearly nine miles since the 1990s. It is believed to hold a large amount of water, that if it were to completely melt would raise sea levels by more than 2 feet around the globe and could unleash more water if neighbouring glaciers are disturbed. Now, new research carried out at the location in West Antarctica that deeper cracks are beginning to form on the shelf of the glacier potentially compromising its intergrity, as published in a study on the science journal Nature. Scientists used a robot named 'Icefin' to bore 2000 ft down below the glacier's surface to get a better look at what is going on beneath it by taking photos and videos as well as collecting valuable pieces of data about temperature and sea levels. What they found wasn't very reassuring. Although the rate of the melting wasn't as fast as they had originally feared the researched still painted a "very nuanced and complex picture." Speaking to CNN, lead researcher Peter Davis said: "The glacier is still in trouble. What we have found is that despite small amounts of melting there is still rapid glacier retreat, so it seems that it doesn’t take a lot to push the glacier out of balance." However, it wasn't all doom and gloom as robot creator and scientist Britney Schmidt of Cornell University, revealed that signs of life had been found on the glacier. She said: "To accidentally find them here in this environment was really, really cool. We were so tired that you kind of wonder like, ‘am I really seeing what I’m seeing?'. "You know because there are these little creepy alien guys (the anemones) hanging out on the ice-ocean interface. In the background is like all these sparkling stars that are like rocks and sediment and things that were picked up from the glacier. And then the anemones. It’s really kind of a wild experience." That being said, Oregon State University ice researcher Erin Pettit, who didn't work on the study believes that the findings are a cause for concern. She told Associated Press: "Thwaites is a rapidly changing system, much more rapidly changing than when we started this work five years ago and even since we were in the field three years ago. I am definitely expecting the rapid change to continue and accelerate over the next few years." Have your say in our news democracy. Click the upvote icon at the top of the page to help raise this article through the indy100 rankings.

By Foo Yun Chee BRUSSELS Twitter cannot run away from its obligations even after quitting a voluntary EU

Apple Inc.’s new $3,499 Vision Pro headset looks just as sleek in person as in its promotional videos,

Shares of chip designer Arm Holdings are trading just ahead of the IPO price. A flock of Wall Street analysts are backing the stock to rise from here.

STAFFORD, Texas--(BUSINESS WIRE)--Jul 11, 2023--

Oil executives betting they’ll be able to meet net zero emissions goals by relying on carbon-capture technology are

Our top picks BEST BUDGET MONITOR KOORUI 24-inch curved monitor (opens in a new tab)

TL;DR: The iRobot Roomba 692 robot vacuum is on sale for $164.99 this Prime Day,

CHESTERBROOK, Pa.--(BUSINESS WIRE)--Sep 21, 2023--

HERNDON, Va.--(BUSINESS WIRE)--Jul 24, 2023--