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

BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

github.com

Post reply on HN
Print view View original

281–290 of 301 posts

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#281

Post by addcommitpush »

cwkoss wrote: post #164
adelie wrote: post #73

Earlier quoted context omitted.

my main issue is the people making hiring and budget decisions aren't 3D artists, they're managers. my work might be objectively better than GPT's, but is that going to matter when my boss compares the cost difference and decides GPT is 'good enough'?

When your boss gets fired for delivering garbage it will matter

Will they, though? Automation has replaced highly expensive, artisanal, high quality things with much more cheaply made, worse quality things. And yet we buy the latter because the quality-to-price ratio is much better.

Most clothes people wear are garbage compared to bespoke clothes. Most industrial food is garbage compared to what a chef might make. And yet.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#282

Post by wizzwizz4 »

riku_iki wrote: post #253
sebzim4500 wrote: post #185

Earlier quoted context omitted.

True, but you are verifying that the code meets some formal criteria, not that it actually does what you want.

formal criteria defines what you want.

Pray, Mr. Babbage, if you verify the wrong properties, will the right answer come out?

Only some software is possible to verify, and there are many properties that it's impossible to verify because the software isn't the only thing that exists in the universe. No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer.

And: just because something's theoretically possible, that doesn't mean an AI system would automatically pick up the ability to do it. Verifiable software in practice is still way behind what we currently know to be possible.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#283

Post by westoncb »

SanderNL wrote: post #212
westoncb wrote: post #139

Earlier quoted context omitted.

The idea is you wouldn’t formulate the proof, you’d describe what want proven and it would generate the proof.

If the machine is that clever I would worry about other things. You definitely wouldn't need to ask anything of it anymore. Besides maybe.. "make all these entrepeneurial types obsolete." Poof!

It's a matter of degree: you can probably already get GPT4 to generate simple proofs; I'm not expecting it to break new ground in mathematics. What I'm getting at is just that the usage is declarative: you'd be describing what you want, not the details of some particular mathematical formulation (though you would likely iterate, making references to formulation details, but still speaking mostly in natural language).

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#284

Post by chaxor »

toxicFork wrote: post #162
chaxor wrote: post #124

Earlier quoted context omitted.

This sounds like reducing the temperature with more steps

Reducing temperature doesn't automatically result in correctness, it only results in more precision. It could be inaccurate with high precision - like a bow that consistently undershoots, and you would have a harder time trying to correct it.

You're right, and I understand that - but you're less likely to get the same result with high temperature, so it will be hard to find correct outputs when using overlap of output. But combining pieces that look good to you of several outputs is a good way to use it. Much of the natural language it creates is useful to me as essentially an extended thesaurus, or to make slightly different points I hadn't thought of it emails. It undoubtedly (demonstrably and probably, I'm sure) knows *way* more than any human on Earth, so it's great at teaching people new things. I usually just reword everything slightly that GPTs provide, so it's a *phenomenal* learning tool.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#285

Post by riku_iki »

wizzwizz4 wrote: post #282
riku_iki wrote: post #253

Earlier quoted context omitted.

formal criteria defines what you want.

Pray, Mr. Babbage, if you verify the wrong properties, will the right answer come out? Only some software is possible to verify, and there are many properties that it's impossible to verify because the software isn't the only thing that exists in the universe. No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer. And: just because something's theoretically possible, that doesn't mean an A…

> No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer.

you can infer algorithm failure rate depending on other input factors as an input. Say you found algorithm will fails every 10e15 years of continues run, you can accept such algorithm as reliable.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#286

Post by barking_biscuit »

junon wrote: post #173
barking_biscuit wrote: post #113

Earlier quoted context omitted.

>I don't really agree with their level of "open"ness I see this complaint a lot, but after watching a lot of interviews with the founders, I think they have by and large taken the right approach. They're trying to drip feed things at a rate that allows it to be digested enough by all parties before releasing more. They actually appear to be quite principled thinkers on this topic.

I think the "holier than thou" approach is rather narcissistic personally. Their rationale has basically been that the world isn't ready, which is rather ridiculous to me.

>I think the "holier than thou" approach is rather narcissistic personally.

This seems like a rather shallow interpretation. What's the actual claim here? That Sam Altman, Greg Brockman, and Ilya Sutskever all have narcissistic personality disorder?

If you were in there shoes, what would you do and what would the rationale be? What might some of the consequences be?

From listening to interviews with them, they seem to be cognizant of the fact that all of this tech will inevitably get into the hands of the public one way or another. They seem mostly to be trying to give people as much time to process the shift that's happening, think through potential implications, and try to adjust as necessary.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#287

Post by DrewADesign »

tekknik wrote: post #268
DrewADesign wrote: post #244

Earlier quoted context omitted.

I think you drastically underestimate the intellectual component of other people's work behind the tools they use to perform it.

In some industries sure, in many others it’s just mindless repetition. The argument is that AI is to free up their time so they can do more important things. Regardless, less demand means less wages across the board. Those that are intelectuales capable of doing more will look to the higher paying jobs once AI automates theirs away.

That those jobs exist and might be automated doesn't negate the existence of all the others. One selfish benefit I see in this will be the hubris of my fellow software developers being taken down a few hundred notches when the market for commodity software development collapses.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#288

Post by wizzwizz4 »

riku_iki wrote: post #285
wizzwizz4 wrote: post #282

Earlier quoted context omitted.

Pray, Mr. Babbage, if you verify the wrong properties, will the right answer come out? Only some software is possible to verify, and there are many properties that it's impossible to verify because the software isn't the only thing that exists in the universe. No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer. And: just because something's theoretically possible, that doesn't mean an A…

> No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer. you can infer algorithm failure rate depending on other input factors as an input. Say you found algorithm will fails every 10e15 years of continues run, you can accept such algorithm as reliable.

> depending on other input factors

You're assuming we've solved physics, and that it would be tractable to model all of that. We haven't, and it probably won't be.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#289

Post by riku_iki »

wizzwizz4 wrote: post #288
riku_iki wrote: post #285

Earlier quoted context omitted.

> No amount of mathematical proof on an ideal RAM machine will anticipate rowhammer. you can infer algorithm failure rate depending on other input factors as an input. Say you found algorithm will fails every 10e15 years of continues run, you can accept such algorithm as reliable.

> depending on other input factors You're assuming we've solved physics, and that it would be tractable to model all of that. We haven't, and it probably won't be.

that's the best approach we can use.

Re: BlenderGPT: Use commands in English to control Blender with OpenAI's GPT-4

#290

Post by SanderNL »

westoncb wrote: post #283
SanderNL wrote: post #212

Earlier quoted context omitted.

If the machine is that clever I would worry about other things. You definitely wouldn't need to ask anything of it anymore. Besides maybe.. "make all these entrepeneurial types obsolete." Poof!

It's a matter of degree: you can probably already get GPT4 to generate simple proofs; I'm not expecting it to break new ground in mathematics. What I'm getting at is just that the usage is declarative: you'd be describing what you want, not the details of some particular mathematical formulation (though you would likely iterate, making references to formulation details, but still speaking mostly in natural language).

I understand, thanks for the clarification. What I like to add is that our reality is a competitive one. If everybody can say “do this general thing”, what is the competitive edge? It’s all relative.

We as humans are not just in the business of solving general problems. We are competing with each other. We need to be faster than the slower ones to survive. (I like to change that but that is not a technical issue.)

One of the ways to compete is to “talk faster” with it. Iterate quicker than the competition. How? I daresay we might get there faster by talking in some sort of modified language.. a code of sorts..

Another way to compete is to become a deep domain expert. Expert of what exactly, if AI is doing it all? Human psychology?

I guess I am just interested in the competitive aspect of it. I have no idea what will happen, but definitely curious what will be possible.

Post reply on HN