markdog12

> opinionated on-device intelligence

> Hate speech triage. On-device moderation that flags hateful, abusive and threatening text

What could go wrong here?

I've tested it extensively for actual local development for my job, and hard disagree here. It's a waste of time to use it. Wish it were not true.

This software has been terrible for me. Burns tokens like crazy, and fails. Most times I try to use the browser plugin, it just says it can't use the plugin. When it does work, it takes minutes to click a button. Unusable workflow.

I ask to generate a png with an alpha channel. It can't. Instead, it outputs a chroma-keyed image, then generates a python script to remove chroma key (fails), then a js script (which also fails). Then my 5h allotment is up.

It's frustrating because if it worked as they advertise, it'd be an amazing tool.

100% agree. I've spent many hours testing out local models/harnesses. So far, they're very much not worth the tradeoff. Obviously, I hope that changes.

Came here to say the same thing. Why add this fake image?

"AI overly affirms users, and that's bad" - everyone nods. "Modern society overly affirms people, and that's bad" - ....

Why did so many people swallow this crap in the first place?

Ah, I think I searched for "jpegxl", that's why there was no match.

"Yes, re-opening.".

> Given these positive signals, we would welcome contributions to integrate a performant and memory-safe JPEG XL decoder in Chromium. In order to enable it by default in Chromium we would need a commitment to long-term maintenance. With those and our usual launch criteria met, we would ship it in Chrome.

https://groups.google.com/a/chromium.org/g/blink-dev/c/WjCKc...

I asked Gemini "dymamic view" how SynthID works: https://gemini.google.com/share/62fb0eb38e6b

OK, I just used https://gemini.google.com/app, I wonder if it's the same there.

Ah, I should have mentioned it was a slow motion video.

> The default FPS it's analyzing video at is 1

Source?

I asked it to analyze my tennis serve. It was just dead wrong. For example, it said my elbow was bent. I had to show it a still image of full extension on contact, then it admitted, after reviewing again, it was wrong. Several more issues like this. It blamed it on video being difficult. Not very useful, despite the advertisements: https://x.com/sundarpichai/status/1990865172152660047

Dart for a long time now.

Whoa, you can now search clipboard history. Go to Spotlight Search, Command+4. You'll get a list of entries, each with a copy button, and is searchable. Even shows the app it was copied in.

All depends on your app, of course. My point is having additional overhead for every gl call is pretty bad.

Yeah, it's very unfortunate for WebGL/WebGPU apps, where every call has to pass/convert typed arrays and issue a js gl call. It pretty much kills any advantage of using WASM. Hope that changes.

Interesting, I have the latest update and I don't see it in the models list.

I have a Model 3 2024 and the "ride quality" is beyond any other vehicle I've been in. I genuinely get a little excited every time I drive it. Best car I've ever been in or drove, and it's not close.

Why do the AI web apps not have voice mode?

Similar experience here. Started taking it around a month ago. The strength gains I've had in that short amount of time have been nothing short of shocking to me.

Interesting, I've been asking it to generate some Dart code, and it makes tons of mistakes, including lots of invalid code (static errors). When pointing out the mistakes, it thanks me and tells me it won't make it again, then makes it again on the very next prompt.

Note this is for the current common approach, not the new approach.

Not in Canada, either :(