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

181–190 of 301 posts

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

#181

Post by TeMPOraL »

juvvel wrote: post #161
singularity2001 wrote: post #146

Earlier quoted context omitted.

GPTs with access to budget

So any and all commerce just becomes a different form of stock trading? I doubt it. People will still need and want tangible things.

> People will still need and want tangible things.

And that matters to who, and why, exactly?

Once enough of the economy is automated, there's hardly a reason for it to keep humans in the loop. It can just run in a circle, serving itself. Humans, meanwhile, will just have to barter for scraps amongst themselves.

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

#182

Post by quchen »

cwkoss wrote: post #165
ChancyChance wrote: post #19

I'm glad it is not just me who thinks I need to "thank" chatGPT or encourage it, e.g.: "Great, now do .... " "Great, now do ... ".

OpenAI surely retains conversation logs. When super intelligent AI gains power, I want it to know I've been a good boy.

Pascal’s Wager, AI edition? :-)

https://en.wikipedia.org/wiki/Pascal%27s_wager

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

#183

Post by iamflimflam1 »

I see a lot of people asking how does this work. The method he is using is one shot learning. He has a prompt and an example of what the interaction should look like.

You can see the prompt here: https://github.com/gd3kr/BlenderGPT/blob/main/__init__.py

It is really easy to build this kind of thing - I've got a very simple command line chatbot that should be very understandable and you can easily play with the prompt.

https://github.com/atomic14/command_line_chatgpt

I would also recommend that people try out the openai playgrounds. They are great for experimenting with parameters.

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

#184

Post by IanCal »

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…

I'm in a similar boat. I'm currently building setups to have GPT-n write code, and it's surprising how good it really is, and in such a short space of time.

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

#185

Post by sebzim4500 »

riku_iki wrote: post #105
wizzwizz4 wrote: post #44

Earlier quoted context omitted.

Chess is fundamentally a different kind of problem. You can prove things about chess in the general case, but it's mathematically impossible to prove things about computer programs in the general case.

> but it's mathematically impossible to prove things about computer programs in the general case. there is such thing as verifiable software.

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

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

#186

Post by IanCal »

Barrin92 wrote: post #76
TeMPOraL wrote: post #28

Earlier quoted context omitted.

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…

For me the interesting job in software is designing architecture and implementing complex things. Automation with tools like this is not remotely there and to some extent probably won't be because we're often talking about human preferences and subjective design choices. Gpt4 in software is Intellisense++ right now, it provides code snippets for things you want to do, it's just raising the bar of abstraction, not rep…

> For me the interesting job in software is designing architecture and implementing complex things. Automation with tools like this is not remotely there and to some extent probably won't be because we're often talking about human preferences and subjective design choices. Gpt4 in software is Intellisense++ right now, it provides code snippets for things you want to do, it's just raising the bar of abstraction, not replacing the designer.

It's not a code writer though, that's not its sole trained task. Why do you think it's going to have a drastically harder time doing the fuzzier higher level work? Human preference and subjective work has a wider acceptance of solutions.

I can have it write abstracts and works of fiction and songs. It wrote a great kids song about bumlollies and their terrible flavour, explained syncitial nuclear aggregates to a lay audience as a jaunty pirate and created ember templates in our custom framework. Have you tried it with any architecture questions?

> Let's be real the entire point of software is to replace labor. The software industry has done it to many sectors of the economy and called it progress. Which it is. We have no right to start complaining now.

It's totally fine IMO to have the views that it's big and scary for me and also good for humanity.

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

#187

Post by Veen »

arecurrence wrote: post #36
EamonnMR wrote: post #31

"The generated code might not always be correct. In that case, run it again lmao" is the best documentation I've read all week.

Copilot has an option (maybe beta users only) to see alternative generations for a prompt. It's really handy because some generations are one-liners while others are entire functions. Perhaps this is infeasible with the current cost per generation but a multiple choice display could be handy (perhaps split the screen into quadrants and pick the one that most fits what you prefer).

Google Bard has a similar feature, and you can ask the OpenAI API to generate multiple completions and pick the best one (best_of) or return some number of the generated completions (n). In OpenAI's case, best of means "the one with the highest log probability per token".

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

#188

Post by therouwboat »

capableweb wrote: post #15
endisneigh wrote: post #11

this is cool, but hm, how should I put it... Ultimately there's a relationship between the preciseness in which you want to control something and the underlying information, as conveyed in language, to describe such precision. Whether you use plain english, or code - ultimately to do things of sufficient precision you will have to be equally precise in your description. I'm sure someone with more time and more knowle…

It could also be that something like this is just another tool in the toolbox. Sure, you could spend time trying to understand Blender's Python API, but lots of Blender users are not programmers. It could be really helpful for them to be able to say "Place 10 spot lights at random position within the boundaries of Mesh 3 with random intensity and color" and just have that appear, rather than having to go looking for…

I dont know why people make this harder than it needs to be, make group of lights, change colors and duplicate, its good enough, no need to use python api.

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

#189

Post by emehex »

kaashif wrote: post #118
pixl97 wrote: post #96

Earlier quoted context omitted.

People in the textile industry were well paid and given a place to live at one point in history. Then the auto loom showed up and they were kicked to the street to starve. I wouldn't want to try to live in any major US city on a blue collar salary.

Maybe one day AI will allow completely unskilled laypeople, ignorant of software, to build and deploy software end to end with no involvement from any software engineers, testers, SREs, anything. That would be the power loom of our time - the power loom allowed unskilled workers to completely replace skilled hand loom weavers with no drop in quality of output. When that's possible, the world will be very different. R…

The problem with this is:

Do you want to listen to a 10 brand new songs by 10 brand new artists using generative AI, or do you want to listen to 10 brand new Taylor Swift songs (that were created with the help of generative AI)?

While some people will be able to leverage this to good effect, I fear the established have much more to gain in this new world…

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

#190

Post by TeMPOraL »

warent wrote: post #71
smilespray wrote: post #24

Earlier quoted context omitted.

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

In the same way that junior artists still exist despite us having moved from MS Paint to Photoshop!

No, that would be comparing to software developers moving from Notepad.exe to proper code editors and IDEs.

The relevant comparison is with junior artists in the age of Midjourney, Stable Diffusion, ControlNet, BlenderGPT, etc. They're facing the same uncertainty as software devs, at the same time, so there isn't much insight to be gained here just yet.

Post reply on HN