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

101–110 of 301 posts

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

#101

Post by georgelyon »

JoeDaDude wrote: post #32

Famous quote: "Wouldn't it be nice if our machines were smart enough to allow programming in natural language?". Well, natural languages are most suitable for their original purposes, viz. to be ambiguous in, to tell jokes in and to make love in, but most unsuitable for any form of even mildly sophisticated precision. And if you don't believe that, either try to read a modern legal document and you will immediately s…

I’ve brought this up in another thread, but we already have evidence that in certain cases it is desirable to trade off specificity for just “getting something done”, that evidence is Python. Python succeeds despite not having a serious type system, because often times you can get something that achieves your goal despite the 25 bugs in your program that would have been caught by a real type system.

On the other side of the coin, there’s C++, which is usually doing the heavy lifting underneath the underspecified-but-sufficient Python code.

My guess is that as LLMs evolve, they will more naturally fill this niche and you will have high-level, underspecified “code” (prompts) that then glued together more formal libraries (like OpenAI’s plugins).

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

#102

Post by whitemary »

purplecats wrote: post #70
Nition wrote: post #61

Earlier quoted context omitted.

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 ho…

The focus blur is repulsive. I think convincing focus blur will be the milestone that replaces stock photography.

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

#103

Post by greenknight »

boppo1 wrote: post #27
bigbassroller wrote: post #2

I know this tech is terrifying to actual 3D artist who don’t want be a “prompt engineer”, but as someone who has never used Blender, I think its cool that I can create something using tools like this and use them in my projects, ex background animation on a website hero section.

I use blender a lot. I know what the api can do. I'm not terrified. Getting anything significant done will still take real work/knowledge because the number of potential 'parameters' of what you can do/make requires that you have the language to describe what you want. Having the posession of that language and knowing how to use blender is a very positive correlation.

Imagine being able to sketch out the outline of what you are after, then say hey blender model it up. Thats what it will get to.

You have a beach, and you want a jetty, just grease pencil approximately where you want it and go Hey thats a jetty build it. and if its not quite right, generate me 50 different versions and ill pick the best.

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

#104

Post by wefarrell »

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…

When Siri, Alexa, and Google home came out I was convinced voice would be the next paradigm shift in human computer interactions, comparable to mobile, but the voice assistants fell short and I was disappointed.

Now it's clear that the shift is coming and it will revolutionize the way we interface with machines.

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

#105

Post by riku_iki »

wizzwizz4 wrote: post #44
kypro wrote: post #26

Earlier quoted context omitted.

This isn't how it will play out though. At first chess AIs got enough to beat unskilled players. They they were good enough to beat intermediate players. Then they challenged the grandmasters. Today no human, no matter how long they practise or how hard they train will ever get close to beating an AI at chess. Your assumption that this raises the bar for human 3D artists is correct today, but it won't be long before…

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.

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

#106

Post by ehnto »

georgelyon wrote: post #101
JoeDaDude wrote: post #32

Famous quote: "Wouldn't it be nice if our machines were smart enough to allow programming in natural language?". Well, natural languages are most suitable for their original purposes, viz. to be ambiguous in, to tell jokes in and to make love in, but most unsuitable for any form of even mildly sophisticated precision. And if you don't believe that, either try to read a modern legal document and you will immediately s…

I’ve brought this up in another thread, but we already have evidence that in certain cases it is desirable to trade off specificity for just “getting something done”, that evidence is Python. Python succeeds despite not having a serious type system, because often times you can get something that achieves your goal despite the 25 bugs in your program that would have been caught by a real type system. On the other side…

I think there exists room for an intermediate layer, a framework for AI to write code in specifically. With larger "target" code blocks it can stitch together. Code is designed around humans to allow them to write specific, abritrary and precise logic with a lot of minuate, but LLMs might be better off thinking in larger business logic blocks that are testable and "sanctioned" by the framework makers for the specific problem domain.

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

#107

Post by whitemary »

whateveracct wrote: post #58
JoeDaDude wrote: post #32

Famous quote: "Wouldn't it be nice if our machines were smart enough to allow programming in natural language?". Well, natural languages are most suitable for their original purposes, viz. to be ambiguous in, to tell jokes in and to make love in, but most unsuitable for any form of even mildly sophisticated precision. And if you don't believe that, either try to read a modern legal document and you will immediately s…

I really feel this. Whenever I try to use ChatGPT, I feel both slow and strained. My usual workflow involves me thinking very few English sentences in my head - I move faster thanks to abstract thought, and I don't think I'm alone.

Same. Somewhat ironically, my art school vocabulary has come in very handy when writing art generator prompts.

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

#108

Post by Pxtl »

georgelyon wrote: post #101
JoeDaDude wrote: post #32

Famous quote: "Wouldn't it be nice if our machines were smart enough to allow programming in natural language?". Well, natural languages are most suitable for their original purposes, viz. to be ambiguous in, to tell jokes in and to make love in, but most unsuitable for any form of even mildly sophisticated precision. And if you don't believe that, either try to read a modern legal document and you will immediately s…

I’ve brought this up in another thread, but we already have evidence that in certain cases it is desirable to trade off specificity for just “getting something done”, that evidence is Python. Python succeeds despite not having a serious type system, because often times you can get something that achieves your goal despite the 25 bugs in your program that would have been caught by a real type system. On the other side…

Not only that, but one of the big successes of chat AIs is their conversation. When a program does something wrong, it's hard to figure out what you said wrong.

When a char AI misunderstood you, it's often quite easy to explain where the misunderstanding happened and the AI will correct itself.

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

#109

Post by jxf »

lwhi wrote: post #59
jxf wrote: post #52

Earlier quoted context omitted.

While I agree, I don't think this is what Dijkstra was speaking about. A lot of the "AI interfaces" are just underpinning the real technical representation. For example, if you say "Which customers recently bought product #721?" this might generate a SQL query like "select * from customers where ...". The interface is not the ChatGPT text box; it's SQL. The ChatGPT text box is just an assistant to help you do the cor…

Your example isn't very comparible to tasks involved in creating, texturing, lighting, animating and rendering 3D models using spline and mesh topologies.

I would say it's applicable to anything with a programming language or DSL for it, which this does.

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

#110

Post by thomastjeffery »

JoeDaDude wrote: post #32

Famous quote: "Wouldn't it be nice if our machines were smart enough to allow programming in natural language?". Well, natural languages are most suitable for their original purposes, viz. to be ambiguous in, to tell jokes in and to make love in, but most unsuitable for any form of even mildly sophisticated precision. And if you don't believe that, either try to read a modern legal document and you will immediately s…

Yes and no. You've provided an excellent introduction to the problem space, but I think natural language has a larger role in formalisms than you might expect.

The most familiar formal language grammars to most people here are programming languages. The difference between them and natural language has been categorized as the difference between "context-free grammar" and "context-dependent grammar".

The most popular context-free language is mathematics. The language of math provides an excellent grammar for expressing logical relationships. You can take an equation, write it in math, and transform it into a different equivalent representation. But why? Arithmetic. The Pythagorean Theorem would be wholly inconsequential if we didn't have an interest in calculating triangles. The application of math exists outside the grammar itself. This is why you, and everyone else here, grew up with story problems in math class.

Similarly, programming languages provide excellent utility for describing explicit computational behavior. What they are missing is the reason why that behavior should exist at all. Programs are surrounded by moats of incompatible context: it takes explicit design to coordinate them together.

If we can be explicit about the context in which a formalism exists, we could eliminate the need for ambiguity. With that work done, the incompatibility between software could be factored out. We could be precise about what we mean, and clear about what we infer. We could factor out all semantic arguments, and all logically fallacious positions. We could make empathy itself into software. That is the dream of Natural Language Processing.

I think that dream is achievable, but certainly not through implicit text models (LLMs). We need an explicit symbolic approach like parsing. If you're interested, I have been chewing on an idea that might work.

Post reply on HN