Stories play a pivotal role in human communication, shaping beliefs and morals, particularly in children. As parents increasingly rely on large language models (LLMs) to craft bedtime stories, the presence of cultural and gender stereotypes in these narratives raises significant concerns. To address this issue, we present Biased Tales, a comprehensive dataset designed to analyze how biases influence protagonists' attributes and story elements in LLM-generated stories. Our analysis uncovers striking disparities. When the protagonist is described as a girl (as compared to a boy), appearance-related attributes increase by 55.26%. Stories featuring non-Western children disproportionately emphasize cultural heritage, tradition, and family themes far more than those for Western children. Our findings highlight the role of sociocultural bias in making creative AI use more equitable and diverse.

Bias benchmarks are a popular method for studying the negative impacts of bias in LLMs, yet there has been little empirical investigation of whether these benchmarks are actually indicative of how real world harm may manifest in the real world. In this work, we study the correspondence between such decontextualized "trick tests" and evaluations that are more grounded in Realistic Use and Tangible {Effects (i.e. RUTEd evaluations). We explore this correlation in the context of gender-occupation bias--a popular genre of bias evaluation. We compare three de-contextualized evaluations adapted from the current literature to three analogous RUTEd evaluations applied to long-form content generation. We conduct each evaluation for seven instruction-tuned LLMs. For the RUTEd evaluations, we conduct repeated trials of three text generation tasks: children's bedtime stories, user personas, and English language learning exercises. We found no correspondence between trick tests and RUTEd evaluations. Specifically, selecting the least biased model based on the de-contextualized results coincides with selecting the model with the best performance on RUTEd evaluations only as often as random chance. We conclude that evaluations that are not based in realistic use are likely insufficient to mitigate and assess bias and real-world harms.

The problem with Bluey is there's not enough of it. Even with 151 seven-minute-long episodes of the popular children's animated show out there, parents of toddlers still desperately wait for Australia's Ludo Studio to release another season. The only way to get more Bluey more quickly is if they create their own stories starring the Brisbane-based family of blue heeler dogs. The London-based developer and father used OpenAI's latest tool, customizable bots called GPTs, to create a story generator for his young daughter. The bot, which he calls Bluey-GPT, begins each session by asking people their name, age, and a bit about their day, then churns out personalized tales starring Bluey and her sister Bingo.

I've written about technology for 25 years and I have never encountered anything as fascinating as ChatGPT. Seeing its responses often gives me a sense of vertigo, like everything is moving too fast. And everything has just got a little bit faster. Last night, OpenAI announced and launched the latest version of the model which underlies ChatGPT, GPT-4. The new version brings several advanced capabilities, including the power to ace legal exams, understand images and digest prompts up to 25,000 words long.

Your Amazon Echo can help you get some much-deserved rest. It can be tricky trying to fall asleep when you have a million things running through your head. Did I remember to send that email? Should I have done that differently? It's enough to keep anyone up at night, especially if you're not getting enough sleep.

Coding Block Cubroid was a complete success, which was all thanks to our 189 backers who invested, waited patiently and believed in us at every step. We got products shipped in a timely manner for our Coding Blocks but we will be working for an even faster and more smooth shipping process for this project. We are extremely excited to return to Kickstarter in order to make a second success story for Cubroid and Artibo. Artibo's chatbot function allows you to receive natural and clear responses from Artibo when you ask a question or make a request. Using the camera in the AI block, Artibo can decipher and recognize objects and/or images.

Anything is on the table when artificial intelligence is used to craft a Grimm's bedtime story. Botnik Studios has teamed up with meditative app Calm to create a new Grimms-style fairy tale to add to its collection of audio bedtime stories. According to a press release, The Princess and the Fox was made using Botnik's predictive text program, with some actual humans smoothing out the edges and filling in the gaps to make it a cohesive story. You have to pay for the service to hear the whole story, but Calm did release a small snippet, which I've transcribed below: Once upon a time, there was a golden horse with a golden saddle and a beautiful purple flower in its hair. The horse would carry the flower to the village where the princess danced for joy at the thought of looking so beautiful and good.

The Echo family of smart speakers is central to Amazon's consumer-facing deep-learning technology. Did you just unwrap a shiny, new Amazon Echo device? Or maybe you already have one and you're getting a little tired just streaming endless hours of holiday music. You might already know that Alexa can convert teaspoons to tablespoons, time the food you put in the oven and tell jokes you can repeat at work. But the digital assistant in Amazon's Echo speakers is capable of so much more.