Is it really? A 9B model is equivalent? Honest question, as I haven't spent that much time with the 9B variant or Flash 2.5. But that seems like a pretty bold claim for such a small model. I assumed Flash 2.5 was considerably larger, but maybe I'm wrong?
Same, but the front is important for airflow in the Framework Desktop, so I don't think covering it with an e-ink screen would work. But maybe with some space between the screen and the fan intake?
In my opinion - not yet. The local models are getting better all the time, but still aren't quite reliable enough. Also, hardware prices are absurd right now. Once the hardware market settles down and there's a little more progress on local models, maybe in a year or two, I expect things will be a bit different.
I'm running a Strix Halo with 128GB of RAM. It's fun to play with, but the real frontier models are just way better.
If you are on a Mac, check out OmniWM, which has a Niri layout, in addition to one that's more like Hyprland. It has made my work on MacOS much more pleasant.
I am disappointed at the amount of negativity here. HN generally loves an experimental domain-specific language, no matter how janky. To be clear, I don't know if this is janky, but the knee-jerk anti-AI sentiment is not intellectually stimulating.
I'm not a coder, I'm a medical doctor. I see some interesting parallels in how medical students sort themselves into specialties by cognitive style to this new rift in programming with LLMs.
Some people like the deep work, some like managing a steady rain of chaos. There's no one right answer. But I'll tell you that my classmates who are happy as nephrologists are very different to the ones that are happy as transplant surgeons.
I tried it out a bit. Like SQLite, it can be used as an embedded db in a flat file. It will be interesting to see what Apple does with it. Their blog had some great examples using BAML.
Most of this hype appears to be coming from grifters who aren't actually connected to the project. So, it's there, but not the fault of the people doing the work.
This has come up in a few recent statements by the project lead, including scammy memecoins and name-sniping. One source: