SINGAPORE--(BUSINESS WIRE)--Jul 25, 2023--

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

We were right! The new WatchOS is hella focused on widgets. Apple introduced the newest

REDMOND, Wash.--(BUSINESS WIRE)--Nov 14, 2023--

Elon Musk claimed that the media ignores things they don't want to talk about and exaggerate minor events when they wish to

Since Elon Musk acquired Twitter, the company has rarely made its executives available for media

The United Arab Emirates will add more solar power plants and battery storage sites in the oil-rich nation’s

By Anna Tong Alphabet Inc's Google on Wednesday demonstrated an updated core search product that embeds more AI

The Vondel Gulag in Warzone Season 4 Reloaded resembles the classic Verdansk Prison showers Gulag from the original Warzone.

(Reuters) -A county sheriff in Oregon ordered people living on the outskirts of the city of Salem to evacuate on

MILPITAS, Calif.--(BUSINESS WIRE)--Aug 9, 2023--

Elon Musk has introduced new controls to X, formerly Twitter, that allow users to limit who can comment on posts to just paying users. The reply paywall will prevent unverified accounts that do not pay for X Premium from engaging in discussions on certain posts. It is the latest change to the platform that Mr Musk has overseen since taking over Twitter last year and renaming it X. The tech billionaire, who is the most-followed person on X, said the latest limits “should help a lot with spam bots”. Mr Musk has brought about a complete overhaul of the way verification on the platform works since his takeover, removing the legacy blue ticks from celebrities, journalists and politicians, and giving them to anyone who paid a monthly subscription fee. These paying users were also given prominence over non-paying users when appearing in searches, as well as prioritised ranking in conversations. The move comes amid reports that Mr Musk is planning to test new subscription options for X users, which could see the introduction of up to three tiers. Each premium tier will offer different levels of ad exposure, according to a report in Bloomberg, though it is not clear if the price of the top tier will differ from the $11 (£9.60) that it currently costs. Other social media firms are also considering similar subscription models, with both Meta and TikTok among those who will potentially supplement their advertising revenue with a user-funded model. Monthly fees for Meta’s platforms, which include Facebook and Instagram, could cost between €10 (£9) and €13 in Europe, The Wall Street Journal reported last week, and come in response to Europe’s data privacy laws. These laws are seen as a threat to the lucrative business model of showing personalised ads to users, with a spokesperson confirming that Meta was exploring options to “comply with evolving regulatory requirements”. Read More The mystery AI device that could replace your phone Schoolboy almost dies from swallowing magnets for TikTok challenge Woman shares honest review of New York City apartment TikTok mom slammed after making 5-year-old son run in 104 degree heat