Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- If you think about it why is language/image even separate from video?
Isn’t video + audio all you need?
by ex-aws-dude - video is just a group of images (GOP) if the gist is what you're after
- > a model must learn a representation of the world: […] and how events sound
I honestly hope they put an unrealistic amount of wilhelm scream into the learning process, just for fun.
- "Actually, let me be careful placing the rubber sealing. If I do it too roughly, it screams."by bensyverson
- I am very excited for this. 2.3 was excellent and I've seen clips from people who got early access along with reading their reflections on it and I think this will be the new SOTA for home use.by OldMatey
- I thought the clips were real footage until they were dancing in a flooded room.by Gecko4072
- These people are hiring in... Freiburg im Breisgau? Wonder how hiring is working out for them there.by tormeh
- the bay is not the world.by rambojohnson
- You are completely ignorant. This is one of the best places to live and work on earth. Nonetheless, they also have positions in San Francisco for what is worth.by kensai
- there's a reason people call it Flyburg im Nicegau.by toilet
- I think these days not being in the US is a plus for many potential hires.by vrganj
- Freiburg University is pretty well known isn't it?
Hiring in university towns is a pretty standard practice for startups outside SF.
by nl - I live nearby, its an amazing area, one of the sunniest in Germany with perfect landscape. Not sure about the talent pool though but there is a university.by beydogan
- A very beautiful place on earth: one friend who lives there enjoys road biking in the surrounding mountains. Another friend does cross-country skiing in his lunch break (in winter times).by mindhunter
- first AI thing coming from Europe that gives high hopesby make_it_sure
- Is anyone feeding models touch data? It seems the main thing we want the robots to do is touch things, but we are just feeding them audio/video/images. The model has to learn how to touch things despite never having touched anything before. Perhaps that's why they all look so hesitant when they touch things?
- Its faster to just have them simulate touching things, they figure it out way faster that way
- Flux 2 Dev Klein has practically been the best you could use on most commercial hardware so I really hope Flux 3 has a comparable updated open-weights model to it. if not it'd be a great loss to most hobbyists.by Tenoke
- Open-weight plans are near the bottom (Launch section):
- Video and audio generation and editing through APIs and private weight access. (“FLUX 3 Video”) - Action prediction through selected research and commercial partners, beginning with mimic robotics (“FLUX-mimic and FLUX 3 Action”) - Image synthesis and editing through APIs and private weight access. (“FLUX 3 Image”) - Open-weight access to a multimodal backbone, for content creation (video, audio and image) and action prediction. (“FLUX 3 Dev”)by mattmanser - It's incredible how negative and dismissive the comments in here are while here I am thinking the model actually looks impressively capable.
But then again I heard the downers have always been the first to leave their dung comments here so let's see...
- It's possible it's because some people care about the consequences of what we're doing as a society beyond the mindless satiation of curiosity. Nothing wrong with curiosity in my books by the way, but I do think isolating it the way we've done in the technical fields is a dangerous and irresponsible attitude.by vouaobrasil
- Given that Martin Scorsese is now an "advisor", I suspect BFL will continue to position itself as the research lab for filmmakers. This video model, if comparable to Seedance 2.0 won't really make sense as a slop generator, as it's too expensive for that, but it would be part of a projects VFX pipeline.by jarjoura
- Advertisers love these sorts of reactions.
I see nothing here but them TELLING us how great it is. Not showing us.
by muppetman - none of this is exciting compared to holodeck in star trekby drsalt
- I'm a person who is making extensive use of current-gen "smart" LLM for coding tasks and building automation tools, doing some of the drudge work of gluing disparate open source things together into new projects. I'm fairly optimistic about that. Particularly when you have a good harness setup and you know enough about the subject matter to understand when a model has gone into some dead-end of reasoning or has built something that's not quite right.
At the same time, I can see social media is being flooded with absolutely horrid AI slop images and video. I'm much more pessimistic about the practical beneficial real world use of totally artificial image and video generators. It seems the uses that these things are put to when they get into the hands of millions of people are detrimental to society and not a benefit.
by walrus01 - It's probably actually good, but after this stuff with Qwen-Image-3 and it's ability to things like render images that look like they were rendered with LaTeX or compose many things side by side or in depth, maybe it's perhaps not totally in the right direction to only focus on visual stuff.
- It would be interesting to see some time-series sentiment analysis of HN. Subjectively it feels like there's much negativity on HN these days, I hope I'm wrong.by ra
- - Showed close to zero examples of people.
- Frivolous use of the term World Model.
- Claims 20 seconds of video, shows only jumpcuts.
Coming soon!
- Yeah, very weird launch. I was like... where's the videos?by vitorgrs
- > Frivolous use of the term World Model
The term "world model" as it was once used in model-based RL can now apparently refer to anything as silly as linear regression. Then again, the RL folks probably borrowed the term from behavioral scientists before them. It's probably best to simply accept this :/
A similar thing happened to "object oriented" which has been misused by philosophers and visual artists alike.
by smokel