The world's biggest metaverse may, arguably, be Roblox. The platform my kids play almost daily is a continuous playground of increasingly evolving experiences with a vast marketplace. It's also going to become a space where generative AI emerges. Roblox released two new AI tools in the past week, but both are only showing up in the creator-focused Roblox Studio: a coding tool that lets anyone use conversational AI to generate code on the fly; and a way to create material designs just by describing what you want. I watched demos of the new Roblox tools in action, and they're very much in line with what generative AI tools like Midjourney, Dall-E 2 and ChatGPT can already do, as Microsoft and Google have expanded these tools elsewhere.

Last month, Roblox outlined its vision for AI-assisted content creation, imagining a future where Generative AI could help users create code, 3D models and more with little more than text prompts. Now, it's taking its first steps toward allowing "every user on Roblox to be a creator" by launching its first AI tools: Code Assist and Material Generator, both in beta. Although neither tool is anywhere close to generating a playable Roblox experience from a text description, Head of Roblox Studio Stef Corazza told an audience at GDC 2023 that they can "help automate basic coding tasks so you can focus on creative work." For now, that means being able to generate useful code snippets and object textures based on short prompts. Roblox's announcement for the tools offers a few examples, generating realistic textures for a "bright red rock canyon" and "stained glass," or producing several lines of functional code that will that make certain objects change color and self-destruct after a player interacts with them.

Natural language comments convey key aspects of source code such as implementation, usage, and pre- and post-conditions. Failure to update comments accordingly when the corresponding code is modified introduces inconsistencies, which is known to lead to confusion and software bugs. In this paper, we aim to detect whether a comment becomes inconsistent as a result of changes to the corresponding body of code, in order to catch potential inconsistencies just-in-time, i.e., before they are committed to a version control system. To achieve this, we develop a deep-learning approach that learns to correlate a comment with code changes. By evaluating on a large corpus of comment/code pairs spanning various comment types, we show that our model outperforms multiple baselines by significant margins. For extrinsic evaluation, we show the usefulness of our approach by combining it with a comment update model to build a more comprehensive automatic comment maintenance system which can both detect and resolve inconsistent comments based on code changes.

The Pearson distance between a pair of random variables $X,Y$ with correlation $\rho_{xy}$, namely, 1-$\rho_{xy}$, has gained widespread use, particularly for clustering, in areas such as gene expression analysis, brain imaging and cyber security. In all these applications it is implicitly assumed/required that the distance measures be metrics, thus satisfying the triangle inequality. We show however, that Pearson distance is not a metric. We go on to show that this can be repaired by recalling the result, (well known in other literature) that $\sqrt{1-\rho_{xy}}$ is a metric. We similarly show that a related measure of interest, $1-|\rho_{xy}|$, which is invariant to the sign of $\rho_{xy}$, is not a metric but that $\sqrt{1-\rho_{xy}^2}$ is. We also give generalizations of these results.

Stefano Corazza is a computer scientist at Adobe, but when I met him, he was pretending to be an ad exec selling a new cherry-flavored soft drink. But before he could create the ad, he needed a photo of the product. "You design something, then make it, then photograph it, then show the photos to an audience," he says. Unless you're using Project Felix, the 3-D rendering tool Adobe unveiled today. In about five minutes, using little more than two stock images, Corazza whipped up a hyper-realistic image of a bottle of Cherry Blast.