Multimodal AI Agents are AI models that have the capability of interactively and cooperatively assisting human users to solve day-to-day tasks. Augmented Reality (AR) head worn devices can uniquely improve the user experience of solving procedural day-to-day tasks by providing egocentric multimodal (audio and video) observational capabilities to AI Agents. Such AR capabilities can help AI Agents see and listen to actions that users take which can relate to multimodal capabilities of human users. Existing AI Agents, either Large Language Models (LLMs) or Multimodal Vision-Language Models (VLMs) are reactive in nature, which means that models cannot take an action without reading or listening to the human user's prompts. Proactivity of AI Agents on the other hand can help the human user detect and correct any mistakes in agent observed tasks, encourage users when they do tasks correctly or simply engage in conversation with the user - akin to a human teaching or assisting a user. Our proposed YET to Intervene (YETI) multimodal agent focuses on the research question of identifying circumstances that may require the agent to intervene proactively. This allows the agent to understand when it can intervene in a conversation with human users that can help the user correct mistakes on tasks, like cooking, using AR. Our YETI Agent learns scene understanding signals based on interpretable notions of Structural Similarity (SSIM) on consecutive video frames. We also define the alignment signal which the AI Agent can learn to identify if the video frames corresponding to the user's actions on the task are consistent with expected actions. These signals are used by our AI Agent to determine when it should proactively intervene. We compare our results on the instances of proactive intervention in the HoloAssist multimodal benchmark for an expert agent guiding a user to complete procedural tasks.

The Roccat Torch is a fun, flashy microphone for gamers and streamers, or anyone who likes some desktop bling. Don't expect incredible audio quality and you won't be disappointed. Do you need a microphone designed specifically for gamers if you're using it for video games? No, of course not (unless you're looking for a USB microphone for streaming, that is). All-around great choices like the Blue Yeti X are just as good for gaming as they are for podcasting or meetings. But do you want a USB microphone designed with gamers in mind?

Sure, it's easier than ever to start your own video game streaming channel, but that doesn't mean it's easy to be a streamer. There are dozens of factors to consider before pressing that big GO LIVE button on YouTube or Twitch, such as lighting, audio quality, video output and software organization -- and that's just to get on-air. If you want to succeed as a streamer, it also takes practice, charisma, luck and, of course, the proper equipment. While we can't help with the patience, natural talent or social factors that determine who becomes a streaming star, we can recommend the tools to make a channel look as professional as possible from day one. If anyone on your gift list is serious about diving into the business of video game streaming, these are the gadgets they'll be ecstatic to unwrap (and show off on-camera).

This post was done in partnership with Wirecutter. When readers choose to buy Wirecutter's independently chosen editorial picks, it may earn affiliate commissions that support its work. Read Wirecutter's continuously updated list of deals here. At $500, this is the lowest price we've seen for the 49-inch model of this television. It's trended at around $600 when in stock in recent months, and while at just under 50 inches it's a little on the small side, if you have a smaller space or just don't want your TV to overwhelm the rest of your decor, it's a nice option at this discounted price for those who like to game.

Reports have been swirling around Google's development of a subscription-based game streaming service, but a flurry of secret meetings at recent conferences has raised speculation it could soon be revealed. The service, codenamed Yeti, would put Google at the forefront of a new part of the videogame business that lets people play games as they're being streamed, rather than using downloads or disks, a report said. The firm met with big video game companies at the Game Developers Conference in March and took meetings at the E3 gaming expo in Los Angeles a few weeks ago, it has been claimed. It is also believed to be considering buying existing games development studios to bolster the plans. Google is developing a subscription-based game streaming service that could work either on its Chromecast or a Google-made console.

It's called "Yeti," and it's the code name attached to an intriguing rumor about Google's gaming ambitions that emerged this week. The rumor suggests the company is developing its own cloud-based gaming service and home console. As The Information reported, the so-called service would stream games into users' homes from remote servers, allowing users to play on a Chromecast or a new console made by Google. A game console from Google could be a big deal, akin to how Microsoft transformed the gaming business after launching the Xbox in 2001. Still, this week's reporting offered scant details how Google's gaming service might work, what its hardware might look like, and when we'll see the fruits of these efforts.

It was a few weeks before Christmas and time to put my voice assistant to the test: Could I just shout out the gifts I needed to buy without having to get on a smartphone or computer? Alexa, the virtual assistant inside my Echo Dot, is really good at reordering stuff I already bought on Amazon. But asking it to order new items was trickier: I had to be precise and know exactly what I wanted to buy. A test by an AP reporter finds that the virtual assistant Alexa inside the Echo Dot is good at reordering stuff bought previously on Amazon. But asking it to order new items was trickier, and it's definitely not for browsing.

Amazon Alexa has never sounded or looked better. NEW YORK – It was a few weeks before Christmas and time to put my voice assistant to the test: Could I just shout out the gifts I needed to buy without having to get on a smartphone or computer? Alexa, the virtual assistant inside my Echo Dot from Amazon, is really good at reordering stuff I already bought on the online shopping site. But asking it to order new items was trickier: I had to be precise and know exactly what I wanted to buy. There were times I had to rephrase orders until it could understand me.

One of the promises of voice-based computing is the ability to make home automation simpler – something that major tech companies, including Amazon, Apple and Google, are now tackling with their own voice assistants and smart speakers. But their solutions are still somewhat clunky, both in terms of the software interface for configuring your smart home and the voice commands you use to take actions. That's where the startup Josh.ai comes in. The company has now raised $11 million to design a better voice-controlled system for smart homes, and will later this year release its own hardware dedicated to this purpose. Headquartered in Denver with offices in L.A., Josh.ai is the product of serial entrepreneurs Alex Capecelatro, CEO, and Tim Gill, CTO.