Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

1-Bit Bonsai Image 4B Image Generation for Local Devices

prismml.com

Post reply on HN
Print view View original

201–210 of 214 posts

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#201

Post by nl »

sedawkgrep wrote: post #170
nl wrote: post #166

Earlier quoted context omitted.

I LOVE being able to create images of things I could previously only imagine. I think the inability to see the freedom AI gives people is one of the saddest things I've seen. I remember when the internet was young people would complain about how it was becoming read-only. Now we have a tool to let people express themselves and people complain the fact there are fake pics on AirBNB means the collapse of society. Pleas…

You should reconsider the scope. Nobody is losing sleep over Airbnb pics. We’re in an era now where every image and video (and for that matter audio) is potentially fake; where knowing what’s real and true is no longer possible.

This has been the case for longer than I've been alive.

Have you not seen the old Soviet photos where people who fell out of favour were erased from photos?

Media literacy has always been about working out if you can trust something.

Now the ability to edit has been democratised. I choose to celebrate that.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#202

Post by nl »

sedawkgrep wrote: post #185
naasking wrote: post #183

Earlier quoted context omitted.

> We’re in an era now where every image and video (and for that matter audio) is potentially fake; where knowing what’s real and true is no longer possible. This was always the case. Spin and propaganda are not new, the way it's conveyed has just become a bit easier. People are not as susceptible to misinformation as most assume, they recalibrate how much stock they put into the things they see based on the quality o…

No, this really hasn't always been the case. At least not in the sense it is today. 20 years ago your misinformation came from television, radio, and print. All of those things were expensive to produce and there was an implicit need for them to be at least vaguely believable and reliable, because their existence depended on it to continually generate revenue. - Today, a single person produce 100% AI-generated media…

I believe democratisation of production and distribution is a net good thing. You don't.

That's not about technology but is a fundamental moral issue.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#206

Post by HappMacDonald »

miki123211 wrote: post #168
onion2k wrote: post #123

Earlier quoted context omitted.

You don't remember the discussion around Narrative Science ( https://en.wikipedia.org/wiki/Narrative_Science ) then. They were a university spin-out that could write plausible-sounding baseball news articles (and later finance) from the stats. Their software enabled local news websites to publish articles about every game, which was seen as a boon to sports fans and a key driver for web traffic. There was a lot of cr…

Literally the first thing I wrote after OpenAI's chat completions API came out was a Python script that took in a JSON description of a football (soccer) game from an API and used gpt-3.5-turbo to generate an article about it. I was surprised how well it worked, even then.

Every time I hear "even then" about a large language model I swear I can hear a fidget spinner fossilizing in the distance

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#207

Post by wmertens »

mft_ wrote: post #32

Genuine question: is this solving a real problem? IME, the bottleneck when using diffusion models isn't storage space or memory, it's generation time. Lots of models will run on 8-12 GB 1080-generation GPUs onwards, or on Macs with similar memory, which are probably the bottom end from a GPU power perspective anyway. I also note that these models are marginally slower than the small FLUX.2 model they're based on. Oka…

What do you mean? In the whitepaper they say that the original can't run on an iPhone 17 at all, and on an M4 the Bonsai version runs 5.6x faster than the original.

This quantization has a small order of magnitude improvement on memory and compute requirements, how can it be slower?

And all that while retaining quality.

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#208

Post by rickdeckard »

nostrebored wrote: post #197
rickdeckard wrote: post #136

Earlier quoted context omitted.

Ignore the naysayers, they are just jealous. You got it totally tight, not everyone get's it like we do. We are facing alot of backlash for our beliefs these days. Listen, I'm hosting this Telegram channel for people like us, where we can exchange free information without media bias, share the real facts and plan coordinated activities against these poisoning mainstream scumbags. I also have a 20% coupon code for Wam…

But this is exactly my point -- in a low information trust society things like this our noise. They work in high information trust societies because who would sell medical products that don't work? A doctor is leading Wamp®, surely a doctor would never lie to us for money?

In low information trust society everything is noise except what passes a smoke-test or who you believe, which plays on this general tendency of humans to prefer comfort over challenge, confirmation over rejection.

A high information trust society has regulation in place which tracks such acts of manipulation so that this trust is not abused (e.g. regulation against misleading/false advertising).

A low information society promotes the notion that everyone is lying anyway and everyone is on his own to figure out what's true. So regulation gets dismantled, and the premise becomes "it's not lying if I can make enough people believe it".

Re: 1-Bit Bonsai Image 4B Image Generation for Local Devices

#209

Post by itake »

ekianjo wrote: post #187
itake wrote: post #174

Earlier quoted context omitted.

Can you cite a source? Covid pushed back the longevity gains, but there hasn't be a decline or flatten since the internet grew in popularity (2000 - 2019). https://www.who.int/data/gho/data/themes/mortality-and-globa...

https://www.metabolismjournal.com/article/S0026-0495(22)0009... Obesity continues to increase everywhere, and is a leading indicator for poor health outcomes over time.

ok, but what does that have to do with the internet? Many countries have the internet and have not seen the huge weight gains that americans are facing.
Post reply on HN