Here in 2020, internet users have ready access to more news media than at any other point in history. But things aren’t perfect. Click-driven ad models, online filter bubbles, and the competition for readers’ attention means that political bias has become more entrenched than ever. In worst-case scenarios, this can tip over into fake news. Other times, it simply means readers receive a slanted version of events, without necessarily realizing that this is the case.
What if artificial intelligence could be used to accurately analyze political bias to help readers better understand the skew of whatever source they are reading? Such a tool could conceivably be used as a spellcheck- or grammar check-type function, only instead of letting you know when a word or sentence isn’t right, it would do the same thing for the neutrality of news media — whether that be reporting or opinion pieces.
That is what the creators of a new algorithm developed by The Bipartisan Press claims to be able to do. They have built an A.I. that can, they say, predict whether text leans left or right with more than 96% accuracy.
“The A.I., which is based on state-of-the-art technology like BERT and XLNet takes in text input, and outputs a numerical value to denote the bias,” Winston Wang, managing editor at the Bipartisan Press, told Digital Trends. “We used a scale of -1 to 1 for simplicity, where a negative value shows left bias, while a positive value shows right bias. The absolute value of the result shows the degree of bias. For example, an article with 0.8 has a considerable amount of pro-right bias.”
The system uses a variety of A.I. approaches, some of which are described here. The excitement of being able to use A.I. for a task such as this is that it opens up the possibility of assessing news coverage and other content at a scale that would be impossible for human raters. (And, provided it works as well as described, potentially with more consistent accuracy, too.)
Wang said that the team is currently working to create a Chrome browser plugin. This could be used to help educate readers on the biases of news articles they read. The A.I. could also potentially be utilized for better content-recommendation systems. Finally, it could help news writers be aware of biases they may not even realize they have, thereby giving them prompts for more objectivity.
You can check out a demo of the A.I. here. For what it’s worth, this story has “minimal” bias.
San Francisco startup Dimensional advertised for people to walk robot dogs through city streets. The New York Times reported that the job could include carrying a roughly 33-pound robot back to the office if it overheated. A lift home is an awkward requirement for a labor-saving machine.
Keeping the hardware running is only one challenge. Anthropic's robotics tests found that language models mostly failed when controlling joints directly, but did better when directing trained controllers. Giving an AI agent a body doesn't teach it to handle ordinary household objects.
Soon, a mattress protector may be more than a bed cover. Australian medtech company Sleeptite and researchers at RMIT University have received a US patent for FlexiSense, a smart bedding technology that tracks body position and posture to help caregivers identify when older residents may be at risk of falling.
The technology is being developed for Sleeptite’s in-bed monitoring system, REMi, and was recently on display at The MedTech Conference in Boston. A peer-reviewed study in Flexible and Printed Electronics says the sensors can also be made at scale without sacrificing performance or durability.
AI companies spend enormous amounts of time convincing us their technology is safe and secure. But what happens when those same companies become targets of increasingly sophisticated AI-powered attacks? Anthropic, the company behind Claude, is now facing that question. According to a Washington Post report, cybersecurity startup Cathedral discovered vulnerabilities that let its researchers access sensitive information in Anthropic's internal systems.
The researchers used AI agents to identify potential entry points in less than 12 hours. Interestingly, they didn't need to crack Claude itself. Instead, they exploited weaknesses in third-party business applications that Anthropic uses for everyday operations. Anthropic's security testing program disclosed the findings, which allows outside researchers to identify and report vulnerabilities.