Non-paywalled: https://archive.ph/vGVor

Complete Article:
Would you pay $20 a month for access to AI hardware you already own? That appears to be one of Meta’s next bets. This week, it quietly announced that your glasses’ Conversation Focus feature will soon be limited to three hours of use per month, unless you pay for a $19.99 Meta One Premium subscription.

In a help article, the company insists that it won’t require a subscription to use your glasses, period; it’s merely erecting a “rate limit” for certain AI features. Even premium subscribers will only get 15 hours of Conversation Focus per month under that “rate limit,” it claims.

Problem is, Meta’s rate limit is ridiculous. The Conversation Focus feature, which amplifies the voice of the person you’re speaking to so you can hear better in noisy environments, is not something that should plausibly be rate-limited, because it doesn’t use Meta’s servers. It runs on-device, using the chips inside the glasses that you’ve already purchased. I turned off my internet, and it kept working.
Meta’s description of “rate limits.”
Meta’s description of “rate limits.” Image: Meta

Here’s how the company introduced it last year: “[C]onversation focus uses your AI glasses’ open-ear speakers, beamforming technology, and real-time spatial processing to dynamically amplify the voice of the person you’re talking to.”

Not only does it avoid Meta’s servers, but Conversation Focus doesn’t technically require an internet connection at all. I double-checked by turning off my phone’s Wi-Fi and cellular, turning on Airplane Mode, and I was still able to use Conversation Focus just fine by tapping a button on my phone.

Does Meta have some secret licensing deal with another company that costs it money every time a person uses Conversation Focus? Failing that, the rate limit sounds utterly bogus.

Meta is feeling some financial pressure trying to make AI happen, recently laying off around 10 percent of its entire workforce — around 8,000 people — to help offset its AI investment costs. It also recently managed to make three pairs of AI glasses $80 cheaper by nixing the Ray-Ban name. But perhaps ditching the branding isn’t the only way it plans to subsidize that move.

At a time when hardware is getting increasingly expensive, I suppose this isn’t as controversial as Meta quietly beginning to embed a facial recognition upgrade for these glasses in millions of phones, code that it has since quietly removed. Still, I’m filing this under “Meta will ruin its smart glasses by being Meta.”

We asked Meta if it could explain the move and whether the company plans to put other on-device features behind a subscription. Meta did not reply to those questions, but it did reach out to make it even clearer that the subscription is optional. “Most people will use Conversation Focus without hitting the monthly limit. The subscription is for power users who want expanded access and additional benefits like premium device support,” Meta spokesperson Tyler Yee tells The Verge.

“Out of the box, you’ll get core AI features like voice assistant, live translation, look and ask, and more. The subscription simply unlocks more access and more powerful features on your AI glasses. Currently, this only includes expanded access to Conversation Focus and premium device support.”

That “currently” does make it sound like Meta might put more features into a subscription bucket, but it also sounds like a few features will stay out of it.

Great advice.

This timeline is just rediculous. I was really waiting for it as I’m staying on the DDR 4 platform.

In this case, however, we’re talking about streaming platforms, which are pretty much universal across state lines.

No need:

Given the Golden State’s massive sway in the entertainment industry, the new law may strong-arm streamers into shushing commercials nationwide.

Source: https://www.politico.com/news/2025/10/06/dial-it-down-california-forces-netflix-hulu-to-lower-ad-volume-00595663

I currently locally host the vault, but I’m realizing that this could cause problems for my family if something were to happen to me. While not technologically inept, if my server at home crashed they would have no idea how to access it, and they would lose all of the passwords.

This is why I refuse to host critical services for friends and family. Many of my friends and family use my Jellyfin server because if something happens to the TV shows and movies, it’s not a big deal. But passwords? No thank you.

Indeed, AI is a tool, and the human should be an expert who verify its work. What I don’t like are posts about apps that are completely vibe-coded without any thought put into them, which pose dangerous security risks.

That makes sense. Software engineers have gone from being artists (because yes, software architecture is an art) to becoming AI managers. It’s demoralising.

I believe open-source software will continue to provide a refuge for artists.