News for hackers. Stuff that matters.
Re:BlenderGPT: Use commands in English to control Blender wi... by westoncb on Sunday March 26, 2023 @08:54PM (#35321550)
In (language model-backed) natural language interfaces the loss of precision can be made up via iteration. If it were about getting it right on the first try this would be a dead end but there's no need for that restriction.
Re:BlenderGPT: Use commands in English to control Blender wi... by roflyear on Sunday March 26, 2023 @08:58PM (#35321588)
Yeah maybe! Just like if you have enough monkeys iterating on enough keyboards...
Re:BlenderGPT: Use commands in English to control Blender wi... by westoncb on Sunday March 26, 2023 @09:20PM (#35321766)
Just a few monkeys should be fine ;)

If this weren't the case then it wouldn't be possible for (e.g.) the software industry to exist as it does: non-technical folks using natural language are able to converse with engineers who take informal descriptions and turn them into code, often leaning heavily on iteration the bring code and spec into conformance.

Re:BlenderGPT: Use commands in English to control Blender wi... by roflyear on Monday March 27, 2023 @09:21AM (#35326349)
"should be fine" - how do you determine this?

There have been many, many cases where I was not able to get GPT-4 to "understand" my problem. No matter how much I tried (until I hit the rate limit for those hours, anyway).

People are throwing these absolutes around, and it's just not totally true.

Much of an engineer's job is to try and implement the correct solution for imperfect requirements, then to go back and quickly fix things to match the real requirements.

Re:BlenderGPT: Use commands in English to control Blender wi... by btown on Sunday March 26, 2023 @09:51PM (#35321957)
And specifically, if the agent implementing the requested actions has a mental model of the domain that is similar to the mental model held by the imprecise specification writer, then the specification doesn't need to be precise to have a high probability of being implemented right the first time! The miracle here is that LLMs don't even need fine-tuning to get to that level - and that's unprecedented for non-human agents.
Re:BlenderGPT: Use commands in English to control Blender wi... by ZephyrBlu on Sunday March 26, 2023 @09:58PM (#35322016)
Legibility is generally a requirement though. At least is currently is.
Re:BlenderGPT: Use commands in English to control Blender wi... by SanderNL on Monday March 27, 2023 @12:48AM (#35322942)
What makes us think that encoding all functionality using natural language is somehow more compact than using code? Sure, describing a website with a button is easy, but I don’t quite see how you would describe Kubernetes or a device driver without writing a book in “legalese”.

Or try formulating a math proof with natural language.

Re:BlenderGPT: Use commands in English to control Blender wi... by westoncb on Monday March 27, 2023 @01:39AM (#35323228)
The idea is you wouldn’t formulate the proof, you’d describe what want proven and it would generate the proof.
Re:BlenderGPT: Use commands in English to control Blender wi... by SanderNL on Monday March 27, 2023 @07:42AM (#35325402)
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!

Re:BlenderGPT: Use commands in English to control Blender wi... by westoncb on Monday March 27, 2023 @04:00PM (#35331612)
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 wi... by SanderNL on Tuesday March 28, 2023 @12:58AM (#35336119)
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.

Re:BlenderGPT: Use commands in English to control Blender wi... by flangola7 on Monday March 27, 2023 @01:38AM (#35323223)
Who said you need to need to describe Kubernetes? "Make my programs work at any scale". Boom
Re:BlenderGPT: Use commands in English to control Blender wi... by SanderNL on Monday March 27, 2023 @03:40AM (#35323949)
That just.. doesn’t work that way.
Re:BlenderGPT: Use commands in English to control Blender wi... by flangola7 on Monday March 27, 2023 @02:35PM (#35330473)
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 wi... by SanderNL on Tuesday March 28, 2023 @01:01AM (#35336140)
I guess you are right about AGI. I think (hope) that is still off in the distance. We’d have other problems than scaling crud apps, I think.
Re:BlenderGPT: Use commands in English to control Blender wi... by flangola7 on Tuesday March 28, 2023 @07:06AM (#35338767)
>I think (hope) that is still off in the distance.

It's being rumored that OpenAI is currently training GPT-5 which will be ready in December, and that many people in the company think it will be a human or better level AGI. Even if it isn't the consistently supersonic jumps they are making every generation suggests we don't have long until human brains are outmoded legacy hardware.

>We’d have other problems than scaling crud apps, I think.

Ever since I first interacted with the original GPT-3 in 2020 I've had the realization that our future was going to be curtailed and distorted into an inconceivable Escher piece. It seems that future is nearly upon us.

Re:BlenderGPT: Use commands in English to control Blender wi... by SanderNL on Thursday March 30, 2023 @08:40AM (#35371728)
My first encounter with GPT-3 messed me up too. Interesting.

I'm all over the place with this. Some days I think it's no big deal, but sometimes I'll get angsty about it.

Today, for example, I'm using it to generate some animations and stuff I generally don't like dealing with (math problems). I remember spending hours on this and not getting anywhere. This thing makes all that effort seem like handcoding websites in the era of templates.

Whenever it hits my direct line of work I'm like "no way that thing works, see, it did this small thing wrong and it proves it is fundamentally incapable of anything". When I use it for domains outside of my expertise I switch to "yeah, sure, but this was either already exceedingly obvious and/or nonsense busy-work to begin with".

News at 11: developer is arrogant.