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

271–280 of 301 posts

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

#271

Post by quonn »

jsdeveloper wrote: post #203
quonn wrote: post #196

Earlier quoted context omitted.

The JEE exam in India is very advanced, I doubt most Europeans or US students could pass it, even after a year or two at university. So those who enter IIT are already quite good very early.

IIT colleges in themselves are not even in top 100 Universities of the world. If you train a lion in a circus, it won't be the king of the jungle. So if we were to believe your statement: > I doubt most Europeans or US students could pass it, even after a year or two at university. than this allegedly miraclous students are wasting there talents studying in IITs!

There was recently a German math professor who famously compared the JEE to some German standards. It‘s worth looking into.

I say this, having studied at a European university as well as visited IIT and a top US university. These are different traditions with different strength and weaknesses but my point was not to say that IIT is better, it was to put the OP comment into a context.

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

#272

Post by quonn »

gcr wrote: post #215
jsdeveloper wrote: post #203

Earlier quoted context omitted.

IIT colleges in themselves are not even in top 100 Universities of the world. If you train a lion in a circus, it won't be the king of the jungle. So if we were to believe your statement: > I doubt most Europeans or US students could pass it, even after a year or two at university. than this allegedly miraclous students are wasting there talents studying in IITs!

USA and European university rankings have a strong bias against universities in the Global South (especially India), in part because of the stigma against Indian programmers and in part because they're generally wanting to promote US and European universities as the global leaders. If you're going to disparage a university based on nothing but ranking lists run by USA and Europeans, you're missing out. IIT students a…

This is not exactly true either. Some IIT students are terrible programmers, others not. But they do have certain strengths and their math training is very strong.

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

#273

Post by ChancyChance »

terramex wrote: post #197
quchen wrote: post #182

Earlier quoted context omitted.

Pascal’s Wager, AI edition? :-) https://en.wikipedia.org/wiki/Pascal%27s_wager

Roko's basilisk: https://en.wikipedia.org/wiki/Roko%27s_basilisk

That is the 180-degree opposite of Occam's Razor.

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

#274

Post by skybrian »

FractalHQ wrote: post #123
skybrian wrote: post #114

Earlier quoted context omitted.

Chatbots use random number generators to create a variety of output, so it would be a terrible idea to use natural language as "source code" for a code generation tool. Running a chatbot shouldn't happen within a build process, because the results aren't reproducible. Once you have the source code though, you can use a variety of tools to manipulate it and save the result. Using chatbots to make modifications under s…

Can you not provide a seed to an LLM the way you can with some of the image / video generation models I’ve seen?

Yes, probably, if you got one that runs locally. OpenAI doesn’t have a way to do it in their API.

There are other reasons not to do it, like it being an external API that charges money. And even if you got something local and deterministic, the generated code would be less easily tweaked by editing the original prompt than by asking the LLM to make the change you want, or by editing the code directly.

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

#275

Post by N1H1L »

jsdeveloper wrote: post #203
quonn wrote: post #196

Earlier quoted context omitted.

The JEE exam in India is very advanced, I doubt most Europeans or US students could pass it, even after a year or two at university. So those who enter IIT are already quite good very early.

IIT colleges in themselves are not even in top 100 Universities of the world. If you train a lion in a circus, it won't be the king of the jungle. So if we were to believe your statement: > I doubt most Europeans or US students could pass it, even after a year or two at university. than this allegedly miraclous students are wasting there talents studying in IITs!

As someone who attended both an IIT (as an undergrad) and a top 10 US university (for my PhD) - think of IITs as very selective undergrad colleges in the USA, such as Swarthmore or Amherst.

IITs are way more teaching focused than research focused, and are have a very light international student presence - two factors that enormously influence rankings.

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

#276

Post by N1H1L »

pmoriarty wrote: post #214
quonn wrote: post #196

Earlier quoted context omitted.

The JEE exam in India is very advanced, I doubt most Europeans or US students could pass it, even after a year or two at university. So those who enter IIT are already quite good very early.

India's high-stakes exams are also plagued by cheating.[1] So just because someone ostensibly "passed" an exam doesn't mean they actually did. Of course, India's education system is far from the only one where cheating is rampant, which is just one reason to look on credentials and accolades everywhere with a skeptical eye. [1] - https://www.economist.com/asia/2022/05/26/indias-exams-are-p...

Compared to paying lacrosse coaches in Stanford - as if US universities are any better!

Your rich dad endows a building in an Ivy and you are in - and apparently it's all good!

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

#277

Post by flangola7 »

SanderNL wrote: post #160
flangola7 wrote: post #138

Earlier quoted context omitted.

Who said you need to need to describe Kubernetes? "Make my programs work at any scale". Boom

That just.. doesn’t work that way. Edit: besides, if it could work you lose the competitive edge. I could describe a much faster more cost effective system which the machine can implement. And we are off to the races again..

If/when it is a generally capable intelligence it very much does work that way. That's how it worked with humans. We saw that stuff needed to work at scale and created something to achieve that.

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

#278

Post by MilStdJunkie »

elif wrote: post #230
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.

I've been building a ChatGPT project this week and this explanation is so true it made me actually lol. Sometimes it's impressively flawless, sometimes it gets stuck in broken patterns... Even if the inputs are identical. "Monkey around with the prompt and pray" has replaced unit testing.

Exactly my experience. I've asked for some time metrics to see if the repeat is actually taking longer than the work.

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

#279

Post by cwkoss »

quchen wrote: post #182
cwkoss wrote: post #165

Earlier quoted context omitted.

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

God is not inevitable

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

#280

Post by addcommitpush »

kranke155 wrote: post #242
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…

You are absolutely right. The myth that automation does not replace Jobs is just that, a myth. Huge numbers were left unemployed with industrial automation in the US and left unemployable. The technical term is structural unemployment. All it means is you cant retrain 10,000 factory workers to be front end developers, and that even If they find a job its often not as well paid. The two greatest myths of modern capita…

> All it means is you cant retrain 10,000 factory workers to be front end developers, and that even If they find a job its often not as well paid.

An important effect is the speed of change - it _might_ be possible to train the next generation such as those who would have been factory workers become front end developers, but it's an entirely different challenge to take actual factory workers and train them for another job. That is to say, even if in the long run automation doesn't lead to unemployment, the short term effect may be quite different.

Post reply on HN