To meet the demands of content moderation, online platforms have resorted to automated systems. Newer forms of real-time engagement($\textit{e.g.}$, users commenting on live streams) on platforms like Twitch exert additional pressures on the latency expected of such moderation systems. Despite their prevalence, relatively little is known about the effectiveness of these systems. In this paper, we conduct an audit of Twitch's automated moderation tool ($\texttt{AutoMod}$) to investigate its effectiveness in flagging hateful content. For our audit, we create streaming accounts to act as siloed test beds, and interface with the live chat using Twitch's APIs to send over $107,000$ comments collated from $4$ datasets. We measure $\texttt{AutoMod}$'s accuracy in flagging blatantly hateful content containing misogyny, racism, ableism and homophobia. Our experiments reveal that a large fraction of hateful messages, up to $94\%$ on some datasets, $\textit{bypass moderation}$. Contextual addition of slurs to these messages results in $100\%$ removal, revealing $\texttt{AutoMod}$'s reliance on slurs as a moderation signal. We also find that contrary to Twitch's community guidelines, $\texttt{AutoMod}$ blocks up to $89.5\%$ of benign examples that use sensitive words in pedagogical or empowering contexts. Overall, our audit points to large gaps in $\texttt{AutoMod}$'s capabilities and underscores the importance for such systems to understand context effectively.

The fast-moving, dynamic world of artificial intelligence (AI) stands in stark contrast to the slow-moving, conservative world of academia.11 This is particularly clear in the world of AI ethics, where in addition to the industry-academia contrast we also have the meeting of very different academic disciplines, including computer science, philosophy, ethics, and social sciences. The traditions, norms, and values of these disciplines are often at odds with one another, making interdisciplinarity challenging. Take, for example, preprinting, the practice of quickly disseminating research before potentially--but not necessarily--seeking publication in traditional academic journals.a Interdisciplinary conflicts appear when, for example, researchers from a computer science background, where rapid publication of preprints on servers such as arXiv is the norm,2 meet researchers from the social sciences and humanities, where this is less common.1,30

Fox News correspondent CB Cotton has the latest on calls for accountability for social media apps after parents say Snapchat helped facilitate drug sales on'Special Report.' Snapchat rolled out its ChatGPT-powered AI chatbot called "My AI" on Wednesday. The feature was introduced in February and was previously only available to Snapchat subscribers, but will now be available to all, the latest move by a social media company in the quickly evolving artificial intelligence (AI) race. "Snapchat subscribers have been loving My AI, our AI-powered chatbot, sending nearly 2 million chat messages per day to learn more about movies, sports, pets, and the world around them," Snap "Today, we announced My AI is rolling out to Snapchatters globally, now with brand new features," Snapchat's parent company, Snap, wrote in a press release. "My AI is an experimental chatbot," a message to Snapchat users on Wednesday read.

TikTok has rolled a new in-app text-to-image AI generator that lets users type in a prompt and receive an image that can be used as the background in their videos. The effect is called "AI greenscreen" and can be accessed via the short-form video app's camera screen. The new effect was first spotted by The Verge. The launch of the new filter comes as text-to-image AI generators are becoming increasingly popular, especially with the launch of OpenAI's DALL-E 2. It's worth noting that the images that TikTok's AI generator produces are quite basic when compared to the output from notable text-to-image models, including DALL-E 2 and Google's Imagen. TikTok's model produces abstract imagery, whereas DALL-E 2 and Imagen are able to create photorealistic imagery.

About the Author:� I�m Linda and I�m an applied scientist working on safety related problems, like spam and abuse in chat. This is how I built an image classification model to help our internal safety specialists to review custom emotes. If you are interested in working on safety related problems, feel free to reach out to @lindarrrliu Emotes are an indispensable part of the Twitch experience. They�re the (unofficial) official language of Twitch because they pack a ton of meaning and...

As homebound students and teachers looked for online resources during the pandemic, many turned to Scratch, a free coding system for kids developed by the MIT Media Lab. Scratch was already a popular option. It's been around since 2007 as a way to make animations and simple video games by combining Lego-like icons representing different coding functions. But in the 12 months beginning in March 2020--as schools across the country went remote for health reasons--usage spiked, and the number of projects shared on the service rose to 23 million, roughly double the amount from the previous year. Meanwhile the service has been going through some big changes behind the scenes.

As Valentine's Day approaches, couples across the country are preparing for this long-standing tradition--and there's a very good chance they met through online dating. But while dating apps can help people find a partner (or just a fun date), they can also subject users to incredible hate and harassment. Despite the fact that dating apps have accrued significant reach and influence, these companies provide very little transparency around how they keep users safe and how they moderate content. Much of the conversation around online platform accountability focuses on companies like Facebook and Google. But dating apps face many of the same issues.

Dating app Tinder will roll out new safety features that alerts LGBTQ users when they're using its service in a country with discriminatory laws. The new feature keys in on 70 different countries chosen with help from the the International Lesbian, Gay, Bisexual, Trans and Intersex Association and is effective today. Countries under the feature's umbrella include Iran, Saudi Arabia, Sudan, United Arab Emirates, and more. 'We're rolling out a Traveler Alert that will appear when Tinder is opened in one of these locations to ensure that our users are aware of the potential dangers the LGBTQ community faces so that they can take extra caution and do not unknowingly place themselves in danger for simply being themselves,' said the company in a statement. Tinder says the feature works by automatically hiding the user upon entering one of the countries and will appear in the form of an alert within the app.

Online communication platforms are increasingly overwhelmed by rude or offensive comments, which can make people give up on discussion altogether. In response to this issue, the Jigsaw team and Google's Counter Abuse technology team collaborated with sites that have shared their comments and moderation decisions to create the Perspective API. Perspective helps online communities host better conversations by, for example, enabling moderators to more quickly identify which comments might violate their community guidelines. Several publishers have also worked on systems that provide feedback to users before they publish comments (e.g. the Coral Talk Plugin). Showing a pre-submit message that a comment might violate community guidelines, or that it will be held for review before publication, has already proven to be an effective tool to encourage users to think more carefully about how their comments might be received.

SAN FRANCISCO - YouTube said Friday it will stop recommending specious videos such as those claiming the Earth is flat or promoting bogus theories about the Sept. 11, 2001, terror attacks. The global video streaming service planned to modify its viewing recommendation system gradually, starting in the United States and later expanding to other countries. Google-owned YouTube, part of the Alphabet holding, said it is scrutinizing how to reduce the spread of content that comes close to but doesn't quite cross the line of violating its community guidelines. "To that end, we'll begin reducing recommendations of borderline content and content that could misinform users in harmful ways," YouTube said in a blog post. "Such as videos promoting a phony miracle cure for a serious illness, claiming the earth is flat, or making blatantly false claims about historic events like 9/11."