lacoolj

I still must be blind cuz the main page of lmstudio.ai only says to download LM Studio 0.4.19, which I have already

The word "Bionic" is never mentioned on the homepage

Any other ideas?

It says this is a separate app than regular LM Studio but I'm not seeing a way to download it.

Am I blind?

gemma-4-e4b is very good at assistance too, and is local and fast and small (and "free")

I wonder if this means Apple TV will make their show volumes louder finally (aka, standard levels of other apps so I don't need to put my speaker at 39/40 to hear what should be 25/40)

Though, I don't even know if Apple TV has an ad-supported plan. This is mainly wishful thinking here :)

I think it's less "how many are there" and more "how small can we go before the influence is too negligible to matter, or is too small to be affected by anything we could physically do or observe"

I mean, there is definitely no "floor", nor "ceiling". Size infinitely gets smaller and infinitely gets larger. We are probably sitting on top of what super-gigantic humans of astronomic proportions would consider a lepton.

100% agree i wish i could upvote this comment twice

I imagine this is a large open model like GLM5.2 etc

It also helps if you're already vibe-coded and don't have customers to begin with

If this was for JS and not Python I would be all over it for the upcoming NFL/NBA seasons and my stat visualizations

This looks more promising than what Mistral just launched (coincidence?????? i think not.)

This approach feels like it could be used for image gen as well (in some combination). Read/view image, start drawing image using illustrator/inkscape/etc (or just SVG), then fill in with what was missed after

Yeah, but you dont know who is vibe coding and who actually knows the output of what they had LLM make

This leads to lack of trust, which the entire open source community is based on. Even if that vibe coded slop is flawless, the stigma will never go away.

Think of the children. Cuz its been 30 years and we finally think its time ... and this is what fixes it!

Cool. Thanks for the memories, internet.

Inb4 govt intervention

70,900

That was fun! tho a lot were cuz the longer the answer, the more likely it was to be right (for words I had utterly no clue)

Was really hard to stop once started lol

"..ban on smart phones.." "..ban on gen AI.." "..ban on social media.."

yes YES YASSSSSSSSSSSS

Ban all the things for kids. I don't want to be interviewing people in 10 years and decline every candidate because they can't correctly answer the question "You are 50ft away from the car wash. Do you walk or drive?"

I didn't even know you could get access to phone service without basic ID info.

Maybe I haven't tried playing with enough "burner" phones :\

Also blanking on a time when you legitimately need to have a phone and not provide your name... anyone have examples?

This should be in the HN guidelines

> why does that take away from the project?

It's like being offered a big mac at a fine dining restaurant. Yes, big mac is gonna taste fine, maybe you can dress it up nicely even. But the restaurant didn't make it, and you feel cheated for buying it (and in this case, wasting your time thinking someone coded it).

Something just existing isn't the same as something being made by someone with passion and effort beyond a one-shot prompt to Fable 5.

Mimo has your back! 1000 t/s on 1T param model

Just need to wait for this thing to be open sourced :)

lol it won't tho...

https://mimo.xiaomi.com/blog/mimo-tilert-1000tps

Cursor users will note that the privacy setting and data retention is not the same as the other models.

Not sure I should use this for work just yet.

dude, the max version looks like it's finally there. handle bar holding with wings, the left leg is behind the frame while the right is in front of it (correctly).

well done anthropic.

Contrary to other comments, and this post, I am actually seeing even that third pillar torn down. I have an architect who is very good at what he does, who wrote specs for the AI to follow, and other than a couple awkward placements, all the file structure is very sane and maintainable.

We are in trouble. Not from a "no more devs" side, but from a "we only need one of you 7 to remain .." side

Absolute trajedy.

Can someone explain why this is on HN tho

Lol Zed > Cursor but this Cursor > Zed

Bug report. If i click a book on the phone my pseudo cursor goes away! :(

What percentage of this code was written by LLM/AI?

This is probably an adjacent result of this (from anthropic launch post):

> In Claude Code, we’ve raised the default effort level to xhigh for all plans.

Try changing your effort level and see what results you get

I would love more information.

What exactly did the request for information say from DHS? What exactly was the reason for them to look for you specifically (certainly there are many others protesting)? Following up on that, how do others avoid something like this? What red flags should be avoided and how?

There may or may not be a solid answer for any of this. But this article feels like it's made for awareness, when it could also be made for action, with the right details included.

So it's the age of AI. And this seems like a great new benchmark! Lots of text, structured but each item a separate "task". Each thing requiring its own new image + textual representation.

I copy + pasted the whole article (minus the few included images) and added this prompt in Gemini 3 Pro:

> Take each of the following and add an image representing the act being described. The image should be very basic. Think of signs in buildings - exit signs, bathroom door signs, no smoking signs, etc. That style of simplicity. Just simple, flat, elegant vector graphic lines for the chopsticks, hands, bowls, etc.

Google Gemini output: https://gemini.google.com/share/11df1bc53e3d

I think this is pretty dang good for a one-shot run. I also ran this through Claude Opus 4.6 Extended (doesn't generate images directly, so it made an HTML page and some vector icons). Not as good as Gemini IMO. See here if curious: https://claude.ai/public/artifacts/8b6589b3-4da4-4fd5-b862-c...

Anyone able to do this better with a different prompt or model (or both)?

> But I think that’s too long. The patent has already served its purpose well, and I believe that holding on to it any longer benefits nobody.

Damn dude didn't you pay like ... over $10k for that patent?