Well. I will say however that, well, I'm not doubting that this is happening, I mean, the GitHub repo is sitting right there for anyone to see, but, however they are programming it's not just a simple process of sticking the ideas into gpt4. Nust for the last couple days I've been trying to get it to create a Richter scale visualizer, which I thought would be a simple little thing, and it can't do it, and it's literally like trying to get a baby to help you code. Every single iteration is some crazy, literally crazy mispronunciation or misconception of what you're asking it to do, even if you just cut and paste and say, redo code, doesn't work, and then repast your entire idea, it gives you some bizarre permutation. It becomes more performance art really where you're just like, okay, how can this screw it up again this way? It's absolutely crazy to think that these guys are getting these kinds of results out of the ai. Obviously there is something that maybe I don't understand or could do better. But still, this is pretty amazing, yes. But it's still very much a hacker thing. But the true innovation is that the value payload has has moved upwards from the execution layer to the innovation layer, to the idea itself, which is really the interesting thing here I think. Like, I don't know how to code, I often have ideas that are no require coding that I can't execute on, but, this obviously would change that, potentially
This little thing reminds me of a Terrence McKenna quote:
"We are creating a technological entity, and the more we immerse ourselves in its configurations, the more it will become like us, and we like it, until the boundary between us is blurred and the entity is born... And like the fetus—or, yes, poised at the head of the birth canal—we don't know where we're going."
Save your money. Only 3.5 can code, really, and it does a really poor job. I do think that if they can get recursive versions looking at each other's code then maybe they could do something but right now, the amount of quality control you have to do on it come to the amount of redo and just obvious stupid errors is just too much to make it worth it
Agree, and actually it is growing. Just the other night it randomly suggested that it sent code directly to my GitHub grist. It did it twice and then promptly forgot that it could do it and proceeded to act retarded again. They are clearly working on it
Awesome McKenna quote and a very interesting thread to boot. This guy pushed the envelope with psychedelics so incredibly hard and was so eloquent about his experiences that I find him enthralling.
That's quite the pilgrimage and I have too many questions.
Personally I find the limited scope of normie thought hard to deal with even well outside the realm of geopolitics. The peep who instinctively down voted both posts at the mere mention of psychedelics is a perfect example.
I predict a high order of probability that he/she acted on "some kind of towering, Jesus based rage", to quote Hunter S. Thompson and continue the general theme.
I very badly need to get out of the city so I can hear the "scream of the butterfly" to quote Morrison.
I forget what McKenna was up to in Peru. I remember something about cow-pat psilocybe mushrooms and him going on a right proper bender but can't remember if it was there. Was everyone wearing bowler hats?
I use it a lot as a tool to generate code, but not a full program. Basically, it lets me be an engineer, while it goes and fills the role of a code monkey. It's not perfect, but it saves a lot of time and toil.
GPT-4 is not good for code, GPT-3.5 is good.
Also remember if you run out of response, you can tell it "continue previous response".
Well. I will say however that, well, I'm not doubting that this is happening, I mean, the GitHub repo is sitting right there for anyone to see, but, however they are programming it's not just a simple process of sticking the ideas into gpt4. Nust for the last couple days I've been trying to get it to create a Richter scale visualizer, which I thought would be a simple little thing, and it can't do it, and it's literally like trying to get a baby to help you code. Every single iteration is some crazy, literally crazy mispronunciation or misconception of what you're asking it to do, even if you just cut and paste and say, redo code, doesn't work, and then repast your entire idea, it gives you some bizarre permutation. It becomes more performance art really where you're just like, okay, how can this screw it up again this way? It's absolutely crazy to think that these guys are getting these kinds of results out of the ai. Obviously there is something that maybe I don't understand or could do better. But still, this is pretty amazing, yes. But it's still very much a hacker thing. But the true innovation is that the value payload has has moved upwards from the execution layer to the innovation layer, to the idea itself, which is really the interesting thing here I think. Like, I don't know how to code, I often have ideas that are no require coding that I can't execute on, but, this obviously would change that, potentially
This little thing reminds me of a Terrence McKenna quote:
Save your money. Only 3.5 can code, really, and it does a really poor job. I do think that if they can get recursive versions looking at each other's code then maybe they could do something but right now, the amount of quality control you have to do on it come to the amount of redo and just obvious stupid errors is just too much to make it worth it
Agree, and actually it is growing. Just the other night it randomly suggested that it sent code directly to my GitHub grist. It did it twice and then promptly forgot that it could do it and proceeded to act retarded again. They are clearly working on it
Why can only 3.5 code? That seems like a step backwards.
GPT4 expressly says it can't code
Bing uses gpt4 and it can code.
yeah think of it as a coding aid, rather than able to code itself
Awesome McKenna quote and a very interesting thread to boot. This guy pushed the envelope with psychedelics so incredibly hard and was so eloquent about his experiences that I find him enthralling.
The guy was the reason I went to Peru to meet the self transforming machine elves!
What did you learn from them?
That's quite the pilgrimage and I have too many questions.
Personally I find the limited scope of normie thought hard to deal with even well outside the realm of geopolitics. The peep who instinctively down voted both posts at the mere mention of psychedelics is a perfect example.
I predict a high order of probability that he/she acted on "some kind of towering, Jesus based rage", to quote Hunter S. Thompson and continue the general theme.
I very badly need to get out of the city so I can hear the "scream of the butterfly" to quote Morrison.
I forget what McKenna was up to in Peru. I remember something about cow-pat psilocybe mushrooms and him going on a right proper bender but can't remember if it was there. Was everyone wearing bowler hats?
I use it a lot as a tool to generate code, but not a full program. Basically, it lets me be an engineer, while it goes and fills the role of a code monkey. It's not perfect, but it saves a lot of time and toil.
GPT-4 is not good for code, GPT-3.5 is good.
Also remember if you run out of response, you can tell it "continue previous response".