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

61–70 of 301 posts

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

#61

Post by Nition »

sircastor wrote: post #8

Until We started to see LLMs, and the tools that can be created with them, I doubted the possibility of Star Trek's Voice command system. Asking for the computer to clarify some concept, or filter and reduce data sets based on arbitrary data was pure science fiction. Seeing something like this makes me think that the arbitrary holodeck commands "Paris, 1950's, rainy afternoon" is suddenly not a challenging part of th…

Here's an image result from MidJourney for "Paris, 1950s, rainy afternoon". No additional editing, and I intentionally avoided adding any text to the prompt beyond your own.

https://i.imgur.com/IYuh29H.png

Not perfect but man, we're getting pretty close.

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

#62

Post by whitemary »

runevault wrote: post #21

Going to be curious where this goes. As someone who hobby models I get the impression there are certain things modelers would LOVE to be able to just hand to an AI (feel like I saw someone on twitter saying they'd love for it to handle UV unwrapping but I may be thinking of the wrong task). Any time we can get a program to do the repetitive work that is time consuming but not interesting/creative that is a huge win.

Back when I was a 3D modeler, I loved UV unwrapping. It's such a zen activity. It allowed my brain to recharge for some reason.

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

#64

Post by warent »

antibasilisk wrote: post #38
warent wrote: post #9

Earlier quoted context omitted.

I don't think this is "terrifying" to 3D artists any more than github copilot is terrying to us haha, I'm not sure why we engineers have this tendency of imagining every other industry as being populated by superstitious peasants from the dark ages who fear new tools. In my experience the vast majority of people are excited about GPT including artists.

>I don't think this is "terrifying" to 3D artists any more than github copilot is terrying to us haha It sounds more like you're just seriously underestimating the direction GitHub Copilot is headed.

This is such a vague comment that it's pretty near impossible to reply to in a very constructive way.

By my estimation it seems probable that we'll end up in the near future with some Jira integration that has an "auto fix" button on tickets. Possibly PMs or managers will be empowered to replace a large chunk of work that is currently done by people like me... and these things are only the beginning!

If you were thinking of something more severe then I'm curious what you're referring to? Otherwise I'm not sure what your point is.

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

#65

Post by kypro »

junon wrote: post #37

Assuming this requires a premium subscription to chatgpt, this might actually push me to sign up. Never thought I'd see the day I'd pay OpenAI a cent given that I don't really agree with their level of "open"ness.

I actually took a look at the pricing after seeing this. I'm a complete blender noob, but I find myself using it every now and then. Something like this would be great for a lot of the stuff I want it for.

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

#66

Post by warent »

TeMPOraL wrote: post #28
warent wrote: post #9

Earlier quoted context omitted.

I don't think this is "terrifying" to 3D artists any more than github copilot is terrying to us haha, I'm not sure why we engineers have this tendency of imagining every other industry as being populated by superstitious peasants from the dark ages who fear new tools. In my experience the vast majority of people are excited about GPT including artists.

I don't know, maybe I am one of those "superstitious peasants from the dark ages who fear new tools", but I'm increasingly terrified of GPT-4 and future iterations of it as applied to the industry I work with (i.e. software). It does seem to threaten to suddenly eliminate all the interesting parts of the job, a good chunk of openings, and to significantly reduce salaries for the openings that remain - all at the same…

Well I put my foot in my mouth here and apologize for insulting any uncertainty; these are new technologies so uncertainty is normal of course. In retrospect I tend to communicate things online in a much more careless way

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

#67

Post by ericd »

roflyear wrote: post #51
ericd wrote: post #17

Earlier quoted context omitted.

Well, you get precision with imprecise communication via iteration. You walk together toward the correct mutual understanding by successive clarifications.

Sure but GPT certainly cannot actually do this. It can iterate, but in GPT-world that means "give me another response" not "learn from what i'm saying, and give me another response" The issue is, sometimes those two things seem to be the same thing!

Eh? GPT definitely uses the past comments as context, so as you clarify, its responses get much closer to the target. If you haven't tried GPT-4, you absolutely should before having strong opinions about it.

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

#68

Post by Thorentis »

smilespray wrote: post #24
Thorentis wrote: post #20

Earlier quoted context omitted.

It just raises the bar so that 3D artists who are only capable of reproducing the same boring things they saw in YouTube tutorials are no longer considered proficient. The more I think about this trend, the more I think it might be good. Bootcamp devs are no longer good enough for junior roles since a GPT could replace them. Digital media people who learnt via YouTube and have no real talent are no longer skilled eno…

How do you get senior people when juniors no longer have careers?

There will still be junior devs. My comment was only referring to particular types of junior devs. In short, the barrier to entry foe being a junior dev will be higher, and require more CS knowledge, perhaps even more hardware knowledge. No more of this "I made a todo list in react in 2 weeks and am now ready to be a software engineer" rubbish.

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

#69

Post by Thorentis »

ksrm wrote: post #55
Thorentis wrote: post #20

Earlier quoted context omitted.

It just raises the bar so that 3D artists who are only capable of reproducing the same boring things they saw in YouTube tutorials are no longer considered proficient. The more I think about this trend, the more I think it might be good. Bootcamp devs are no longer good enough for junior roles since a GPT could replace them. Digital media people who learnt via YouTube and have no real talent are no longer skilled eno…

It is good when people lose their jobs, actually!

That wasn't my point. It is bad that they will lose their jobs. But that doesn't mean we should keep those jobs around.

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

#70

Post by purplecats »

Nition wrote: post #61
sircastor wrote: post #8

Until We started to see LLMs, and the tools that can be created with them, I doubted the possibility of Star Trek's Voice command system. Asking for the computer to clarify some concept, or filter and reduce data sets based on arbitrary data was pure science fiction. Seeing something like this makes me think that the arbitrary holodeck commands "Paris, 1950's, rainy afternoon" is suddenly not a challenging part of th…

Here's an image result from MidJourney for "Paris, 1950s, rainy afternoon". No additional editing, and I intentionally avoided adding any text to the prompt beyond your own. https://i.imgur.com/IYuh29H.png Not perfect but man, we're getting pretty close.

interesting. i apparently opened that image, then forgot about it, and without context saw it later. i looked at it, thought wow that's a cool picture from back in the day, looked at the people in it, and left.

i now ran into your comment (with a purple link) and did some reflection. upon reexamination, its clear that the picture is fake (because im looking for it) but when i wasn't looking for it, its interesting how all the "hot spots" or interesting pieces of the picture are pretty good and the (imo) lackluster parts are the "less interesting" pieces like the end of the roads where it it blurs out. i wonder if that bias is inherently ingrained in the system.

Post reply on HN