Gen-1: The Next Step Forward for Generative AI — Generating Videos

https://research.runwayml.com/gen1

by davidbarker • 3 years ago

57 34 3 years ago

research.runwayml.com

kilgnad6• 3 years ago

I expect Gen-5 to produce something similar to Avatar 2 from this sentence: "Blue people in science fiction film"... Or maybe you just feed it all the movies as input: Avatar 1 and Avatar 2 and it makes an Avatar 3.

Truly we are witnessing the beginning of the end, yet here I am working on leetcode and practicing my programming skills as if the end wasn't impending. I'm hoping that when it comes (which it will) it will happen either towards the end of my career or well after I'm dead, but I cannot deny the possibility that the paradigm shift can happen within the next decade.

How many people are just acting irrational like me and how many of you are lying to themselves and downplaying AI?

throw12346512342• 3 years ago

See my comment here: https://news.ycombinator.com/item?id=34640699

tl;dr: So far, we might be overplaying AI. The post above can be coupled with the "AI Kessler Effect" in that AI text/code will be basing itself on AI-generated training sets. This will lead to a quality drop without human supervision (same old jobs as search-engine result checking, except maybe more technical). It will also lead to result stagnation - if fewer devs are writing code, then everything is a rehash of old code. Of course, the argument is that devs are writing new code and automating the boring parts, which is somewhat true, but doesn't lead to a loss of jobs.

Also, if anyone knows of companies that they believe to be leading in AI, or products than can generate whole apps, please share.

P.S. I am yet to see AI image generation to build visual novels. That would be the mark of it being "good". I spend very little time in the space though, so again, if anyone knows of anything, please share. (and no, not the kids book about AI, by AI, that is both bad and hand-picked / callibrated out of 1000s of results).

CuriouslyC3• 3 years ago

In the future researchers and big corps will have much more heavily annotated data sets that can provide models with things like aesthetics and accuracy scores, and low quality AI generations won't impact output much unless prompted for (e.g. "early 2020s style AI art image with deformed hands and phantom limbs")

lm284697• 3 years ago

We have a long way to go, remember we're 2 years away from self driving car since 2010.

AGI is always coming "in a decade or so" since the 70s

Nothing says we're on a path to a paradigm shift given the current approach

kilgnad6• 3 years ago

AGI is always coming "in a decade or so" since the 70s

This whole thing is no longer relevant because we just hit certain inflection points that weren't relevant in the past. AI can now code, it can craft essays and it can lie.

In fact nobody talks about this but AI can already passed the turing test. People weren't saying AGI would come out in the next decade or so, they were saying AI would pass the turing test in the next decade or so. Well.... it passed it. Yet here we are setting new goal markers and downplaying the milestone.

I think if you can't acknowledge the the possibility that AI could take over our jobs within our lifetimes, then I think you're not being honest with yourself.

Not saying that it will, but the possibility given the milestones surpassed by AI in the last decade... indicate that it could Must be acknowledged.

cjg• 3 years ago

remember we're 2 years away from self driving car since 2010

Depending on how you define that milestone, we are already there. There are multiple companies offering self-driving cars to the public in multiple cities.

I'd count that as a success.

detrites2• 3 years ago

We have a long way to go

Well maybe we would. But, we're not doing this alone.

We could move the goalposts again but AI already passed the tests we made for it.

This paradigm shift's happened already; present AI is passing undetected versus a human in a rapidly growing list of highly skilled and specialised tasks.

When the list comes to contain "improving AI" it's game over.

swatcoder• 3 years ago

The technology we’re seeing now seems on track to eat up some pretty low-level “art” tasks like pulp copywriting, boilerplate coding, token illustration and design, etc.

There’s little reason to expect a lot more from it any time soon. If you came to software engineering or data science because it looked like a high-paying career for a nerd, and easier to break into then law, medicine, or trading, this isn’t a bad time to hop off.

Hitch your wagon to this AI stuff and you can be a Senior Prompt Engineer in a decade and outearn all of us.

But those of us who enjoy our craft and have genuine expertise don’t really need to worry about anything (except the bursting of a pay bubble that was due soon anyway).

xnx• 3 years ago

Looks like a good application of technology. Note that this isn't generating videos from scratch like Imagine Video (https://imagen.research.google/video/).

notjustme• 3 years ago

RunwayML is such a scam. Their product barely works (seriously - try making a simple video), but their marketing surely does lol. Maybe instead of adding new half-finished features they should just make a few of them work.

nodja• 3 years ago

Weird thing to say when runway and compvis made stable diffusion.

cma• 3 years ago

The short little clips do look a bit misleading, like they are just doing a technique like ebsynth plus periodic regeneration, same thing lots of people did since near day one. We'll have to wait on the paper I guess.

clircle• 3 years ago

Why is it that the AI research that makes it onto this website seems a lot more like marketing than a contribution to the body of human knowledge?

marginalia_nu2• 3 years ago

The grifters all moved onto AI when air went out of crypto. They're desperately trying to fan the flames of another hype cycle so they can cash out again.

The basic premise for such a scheme is a technology that is difficult to understand, especially for laymen. The more it seems like infinitely powerful magic, the better.

throw12346512342• 3 years ago

That boat just sailed away 3 days ago btw: https://www.coingecko.com/en/coins/image-generation-ai

vba616• 3 years ago

"Any sufficiently advanced technology is indistinguishable from a rigged demo"

nullc• 3 years ago

The grifters all moved onto AI when air went out of crypto.

I wish, unfortunately grifters aren't a finite resource.

(surely some crypto grifter will show up now and suggest solving this with a blockchain)

blurbleblurble• 3 years ago

This looks like a distillation of the kinds of techniques a lot of "AI artists" have been using for a while.

sshadow• 3 years ago

I really do look forward to the day in which I can ask to watch Hell's Kitchen with the cast of The Birdcage.

Gen-1: The Next Step Forward for Generative AI — Generating Videos

Related Stories