Last week, I published a story about new tools developed by researchers at AI startup Hugging Face and the University of Leipzig that let people see for themselves what kinds of inherent biases AI models have about different genders and ethnicities. Although I've written a lot about how our biases are reflected in AI models, it still felt jarring to see exactly how pale, male, and stale the humans of AI are. That was particularly true for DALL-E 2, which generates white men 97% of the time when given prompts like "CEO" or "director." And the bias problem runs even deeper than you might think into the broader world created by AI. These models are built by American companies and trained on North American data, and thus when they're asked to generate even mundane everyday items, from doors to houses, they create objects that look American, Federico Bianchi, a researcher at Stanford University, tells me.

The popularity of artificial intelligence firm OpenAI's ChatGPT has caught the attention of cyber attackers now. A recent report by cyber intelligence company CloudSEK has found that threat actors are taking over Facebook accounts and modifying them to appear like authentic ChatGPT page. Using this method, the attackers have been able to gather critical data on users, including personal identifiable information (PII), system information, and credit card details. The attackers use previously compromised data, phishing techniques, and stealer logs to infiltrate Facebook accounts. These Facebook accounts are modified to look like authentic ChatGPT-related pages, by naming them "ChatGPT OpenAI" and setting the ChatGPT image as the profile picture These compromised accounts are then used to distribute malware through different channels like Trello boards, Google Drive, and individual websites embedded in Facebook ads.

It is the whiz-kid of the artificial intelligence (AI) world that others are trying to emulate. In the four months since its November 30 launch, ChatGPT has shown the ability to perform a wide range of tasks, from cracking the bar and medical licensing exams in the United States to writing emails and songs, building apps, and more. The fact that it is freely available for public use has opened up a plethora of opportunities previously thought beyond the realm of possibility of AI -- even though the app's makers have faced criticism for opacity around the programming they have used to train it. Developed by OpenAI, a company backed by Microsoft, ChatGPT became the fastest-growing consumer app in the world two months after its launch, with more than 100 million users by January. That early success has prompted Microsoft to integrate its Bing search engine and Edge browser with the technology running ChatGPT in the hope of improving the experience of users.

For the last decade-plus, the search engine market has been a snooze. The industry has been dominated by Google -- the main subsidiary of technology giant Alphabet (GOOG -2.83%) (GOOGL -2.83%) -- with a 90% market share across internet-connected devices worldwide. Given how profitable the search engine market is, this dominance has enabled Alphabet to print money year after year with remarkable consistency. Now, its largest competitor, Microsoft (MSFT -1.49%), wants a piece of that pie. The owner of the Windows operating system and Internet Explorer (now renamed Microsoft Edge) has made a sizable investment into OpenAI to bring the start-up's disruptive artificial intelligence (AI) chatbot to its Bing search engine.

Join top executives in San Francisco on July 11-12, to hear how leaders are integrating and optimizing AI investments for success. Last week felt like a lifetime in AI. Sure, the week before was fast-paced and so was the week before that, but this one -- really, a lifetime. And somehow I just couldn't let it go. While the rest of the world went about its business, I noodled about the implications of OpenAI's latest ChatGPT chess move.

As a 24-hour global broadcast news company, we opted to use virtual anchors to deliver DeFiance Daily every two hours which eliminated the time and cost of traditional production. With Hour One's AI avatar technology we're able to generate premium video from text, automatically and affordably, allowing us to keep pace with our audiences need for rapid reporting. Now with our custom anchors and a personalized 3D studio environment, we can deliver even more content, all within the platform.

Foundation models (e.g. ChatGPT, StableDiffusion) pervasively influence society, warranting immediate social attention. While the models themselves garner much attention, to accurately characterize their impact, we must consider the broader sociotechnical ecosystem. We propose Ecosystem Graphs as a documentation framework to transparently centralize knowledge of this ecosystem. Ecosystem Graphs is composed of assets (datasets, models, applications) linked together by dependencies that indicate technical (e.g. how Bing relies on GPT-4) and social (e.g. how Microsoft relies on OpenAI) relationships. To supplement the graph structure, each asset is further enriched with fine-grained metadata (e.g. the license or training emissions). We document the ecosystem extensively at https://crfm.stanford.edu/ecosystem-graphs/. As of March 16, 2023, we annotate 262 assets (64 datasets, 128 models, 70 applications) from 63 organizations linked by 356 dependencies. We show Ecosystem Graphs functions as a powerful abstraction and interface for achieving the minimum transparency required to address myriad use cases. Therefore, we envision Ecosystem Graphs will be a community-maintained resource that provides value to stakeholders spanning AI researchers, industry professionals, social scientists, auditors and policymakers.

Recently, it has become progressively more evident that classic diagnostic labels are unable to reliably describe the complexity and variability of several clinical phenotypes. This is particularly true for a broad range of neuropsychiatric illnesses (e.g., depression, anxiety disorders, behavioral phenotypes). Patient heterogeneity can be better described by grouping individuals into novel categories based on empirically derived sections of intersecting continua that span across and beyond traditional categorical borders. In this context, neuroimaging data carry a wealth of spatiotemporally resolved information about each patient's brain. However, they are usually heavily collapsed a priori through procedures which are not learned as part of model training, and consequently not optimized for the downstream prediction task. This is because every individual participant usually comes with multiple whole-brain 3D imaging modalities often accompanied by a deep genotypic and phenotypic characterization, hence posing formidable computational challenges. In this paper we design a deep learning architecture based on generative models rooted in a modular approach and separable convolutional blocks to a) fuse multiple 3D neuroimaging modalities on a voxel-wise level, b) convert them into informative latent embeddings through heavy dimensionality reduction, c) maintain good generalizability and minimal information loss. As proof of concept, we test our architecture on the well characterized Human Connectome Project database demonstrating that our latent embeddings can be clustered into easily separable subject strata which, in turn, map to different phenotypical information which was not included in the embedding creation process. This may be of aid in predicting disease evolution as well as drug response, hence supporting mechanistic disease understanding and empowering clinical trials.

As generative AI and its eerily human chatbots explode into the public realm -- including Google's Bard, released yesterday -- Silicon Valley looks ripe for another big era of disruption. Think about the era of personal computers, or online businesses, or social platforms, when an accessible, unpredictable new idea shakes up the establishment. But unlike earlier disruptions, the reality of the generative AI race is already looking a little … top-heavy. With AI, the big innovation isn't the kind of cheap, accessible technology that helps garage startups grow into world-changing new companies. The models that underpin the AI era can be extremely, extremely expensive to build.

If you believe in the multibillion-dollar valuations, the prognostications from some of tech's most notable figures, and the simple magic of getting a computer to do your job for you, then you might say we're at the start of the chatbot era. Last November, OpenAI released ChatGPT into the unsuspecting world: It became the fastest-growing consumer app in history and immediately seemed to reconfigure how people think of conversational programs. Chatbots have existed for decades, but they haven't seemed especially intelligent--nothing like the poetry-writing, email-summarizing machines that have sprouted up recently. OpenAI has defined the moment, but there are plenty of competitors, including major players such as Google and Meta and lesser-known start-ups such as Anthropic. This cheat sheet tracks some of the most notable chatbot contenders through a few metrics: Can you actually use them? Do they contain glaring flaws?