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

Flux 3 X Mimic: The Next Generation of Video-Action Models

bfl.ai

Post reply on HN
Print view View original

41–50 of 57 posts

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#41

Post by altern8 »

vanviegen wrote: post #30
altern8 wrote: post #28

Earlier quoted context omitted.

That's exactly the ones I like! On Saturdays I watch cheesy horror movies from the 80s. But with my GF I watch whatever is rated >= 8 on Imdb and the 8s from years ago are ALWAYS much, much better than the recent ones. Maybe I just don't like the style. All the over explaining, etc.

I think most movies drop a bit in IMDb score over their first few years. That might (partly) explain it. Or you just prefer older movies . :-)

Interesting! I didn't know that. Could be both, too :-)

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#43

Post by altern8 »

Rebelgecko wrote: post #38
altern8 wrote: post #29

Earlier quoted context omitted.

What's a good recent movie I could watch? Today is Friday

Odyssey is supposed to be pretty good. Main complaint I've seen is that it's not as horny as the source material.

Thank you! I'll take a look

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#44

Post by altern8 »

phoghed wrote: post #34
altern8 wrote: post #29

Earlier quoted context omitted.

What's a good recent movie I could watch? Today is Friday

Was going to pull out my default recommendation of Oldboy but then I realized it’s 23 years old, which just aged me greatly

Welcome to the club! :-)

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#45

Post by stronglikedan »

flufluflufluffy wrote: post #13

Ok the phrasing here, it’s, it’s just - > However, compared to more specialized approaches for representation learning they produce less disentangled representations, which puts a ceiling on their usefulness for tasks that require world understanding. Only an LLM would use a less disentangled representation of the concept “more entangled” when trying to explain to people in the real world why less disentangled repres…

> Ok the phrasing here, it’s, it’s just -

That dash definitely means an LLM wrote this comment. /s

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#46

Post by stronglikedan »

altern8 wrote: post #28
phoghed wrote: post #23

Earlier quoted context omitted.

Survivorship bias, possible that you just aren’t watching all the shitty ones that nobody remembers.

That's exactly the ones I like! On Saturdays I watch cheesy horror movies from the 80s. But with my GF I watch whatever is rated >= 8 on Imdb and the 8s from years ago are ALWAYS much, much better than the recent ones. Maybe I just don't like the style. All the over explaining, etc.

I regularly stream movies from Screambox, FilmRise and Alter as background music while I work from home. I love cheesy horror, but they're just bad enough to keep me company without distracting me

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#47

Post by teodosin »

phoghed wrote: post #24
flufluflufluffy wrote: post #13

Ok the phrasing here, it’s, it’s just - > However, compared to more specialized approaches for representation learning they produce less disentangled representations, which puts a ceiling on their usefulness for tasks that require world understanding. Only an LLM would use a less disentangled representation of the concept “more entangled” when trying to explain to people in the real world why less disentangled repres…

We’re just pulling signs of LLM touched writing out of our ass now. Might be time to move on from the accusations, assume all writing is at least LLM assisted and judge it purely on the quality.

Yeah, as if people haven't used words like "irregardless" way before LLM's already

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#48

Post by doctorpangloss »

altern8 wrote: post #21

This is awesome. What's sad to me is that we have all this awesome technology, but movies are worse than ever. I usually watch movies from decades ago just to find something decent and it's amazing how with goofy-looking puppets the storytelling was 1000 times better. This is probably an unrelated rant, sorry

would you refuse to invest in BFL because Robin Rombach doesn't know anything about making movies?

sora is done. can you find me one person brave enough to say, "Bill Peebles, a nice guy, doesn't know anything about making movies?" this isn't just a VC problem, this is why it is called the Hollywood No, but that said: maybe the hollywood no is the problem? in video games it has been called Toxic Positivity. are you getting it now?

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#49

Post by flufluflufluffy »

flufluflufluffy wrote: post #13

Ok the phrasing here, it’s, it’s just - > However, compared to more specialized approaches for representation learning they produce less disentangled representations, which puts a ceiling on their usefulness for tasks that require world understanding. Only an LLM would use a less disentangled representation of the concept “more entangled” when trying to explain to people in the real world why less disentangled repres…

goddamn people it’s a joke

Re: Flux 3 X Mimic: The Next Generation of Video-Action Models

#50

Post by thomastjeffery »

phoghed wrote: post #34
altern8 wrote: post #29

Earlier quoted context omitted.

What's a good recent movie I could watch? Today is Friday

Was going to pull out my default recommendation of Oldboy but then I realized it’s 23 years old, which just aged me greatly

No Other Choice (by the same director) is incredible, and even relevant to this post.
Post reply on HN