- Joined
- Jun 3, 2015
- Messages
- 2,143
Rep Bank
$2,945
$2,945
User Power: 162%
After spending some time with GPT I have come to understand its limitations. I've mainly been using it for character and place names for my books (also fairly reasonable at coming up with pen names), however recently I reignited my interest in coding (still have ideas burning a place in my skull) so I decided to see if GPT could code some stuff for me.
I decided to test it in the graphics program Blender, which if you don't know is an extremely powerful 3D/Animation opensource software which uses Python.
I asked it a fairly simple question - "code me a generic looking flower"
To say the results were awful, is being extremely kind to GPT, apart from the fact it couldn't understand that the 'diameter' argument is not used in Blender, the final result (which took about thirty-five minutes of repeating myself and wishing GPT was a person so I could slap him) was a floating sphere with a one "atom" thick ring around it. #facepalm.
Next I thought okay, let's go simple, code me a simple head, after which, my head hurt... a lot.
I won't paste the code, but here's a snippet of my infuriating convo with it.
Me - Okay, let's see how you do coding a generic human head shape. Please remember not to use any 'diameter' arguments and please remember to use 4 vector functions for any mat.diffuse lines or similar.
GPT-3 -
Sure! Here's an example of how you could create a basic human head shape:
Code
This code creates a new mesh object for the head, adds a UV sphere to a bmesh, applies proportional editing to shape the head, and then creates a new mesh from the bmesh and sets it as the mesh for the head object. It also sets the color of the head material to a light skin tone using RGBA vector values, and positions the head in the scene and adds it to the scene.
(It did none of those things)
Me - The code returned the following error Python: Traceback (most recent call last): File "\Text", line 23, in <module> ValueError: bpy_struct: item.attr = val: sequences of dimension 0 should contain 3 items, not 4
GPT-3 - I apologize for the error. This might have been caused by using a 4-dimensional vector instead of a 3-dimensional one. Here's the corrected code:
(note: I'd already told it to put in 4 values for something specific, but hey, possibly my bad.)
This code creates a head mesh using a UV sphere, and two eye meshes using circles that are translated to the appropriate positions. The materials for the head and eyes are also set, with the head material having a skin tone and the eyes material being black.
Me - Please rewrite the code without any 'diameter' arguments. (As I mentioned in the first goddamn place!)
GPT-3 - Sure, here's a revised version of the code for creating a generic human head shape without using any diameter arguments:
code
This code uses create_icosphere instead of create_uvsphere to create the head shape without using any diameter arguments. I also added a from mathutils import Vector statement to use the Vector function to set the color of the head material with four float values (R, G, B, alpha).
(Proceeds to make human head so small I can't even zoom in on it.)
Me -
I can hardly see it, rewrite the above code EXACTLY, except make the head ten times bigger
GPT-3 -
Sure! Here's the code with a ten times bigger head:
code
I increased the diameter of the UV sphere to 1.0 to start with, then scaled the head by a factor of 10 at the end using the scale property of the head_obj.
Me - (For the love of God)
rewrite the code without any 'diameter' arguments, remember Blender does not use them any more (like I said in the first f***ing place! Plus rewrite exactly means do the same thing again you moron!)
GPT-3 -
Sure, here's the rewritten code without any 'diameter' arguments:
(I will show you one line of the code it came up with)
bmesh.ops.create_uvsphere(bm, u_segments=32, v_segments=16, diameter=1)
Like, what the actual???? It was like having a conversation with a genius with advanced Alzheimer's.
I even asked it if it could read the changelog if I linked it, GPT said "sure, send me the link." I sent the link and then asked it if it understood what had been put in place instead of the 'diameter' argument.
Yes it said, then proceeded to produce the code above, with the defunct 'diameter' argument.
(Even though this is a tiny fraction of my conversation with GPT-3), this is all a very long way of saying, has anyone tried GPT-4 for coding yet? Is it better than its moronic cousin GPT-3? Or will it just give me the wrong answer faster?
I decided to test it in the graphics program Blender, which if you don't know is an extremely powerful 3D/Animation opensource software which uses Python.
I asked it a fairly simple question - "code me a generic looking flower"
To say the results were awful, is being extremely kind to GPT, apart from the fact it couldn't understand that the 'diameter' argument is not used in Blender, the final result (which took about thirty-five minutes of repeating myself and wishing GPT was a person so I could slap him) was a floating sphere with a one "atom" thick ring around it. #facepalm.
Next I thought okay, let's go simple, code me a simple head, after which, my head hurt... a lot.
I won't paste the code, but here's a snippet of my infuriating convo with it.
Me - Okay, let's see how you do coding a generic human head shape. Please remember not to use any 'diameter' arguments and please remember to use 4 vector functions for any mat.diffuse lines or similar.
GPT-3 -
Sure! Here's an example of how you could create a basic human head shape:
Code
This code creates a new mesh object for the head, adds a UV sphere to a bmesh, applies proportional editing to shape the head, and then creates a new mesh from the bmesh and sets it as the mesh for the head object. It also sets the color of the head material to a light skin tone using RGBA vector values, and positions the head in the scene and adds it to the scene.
(It did none of those things)
Me - The code returned the following error Python: Traceback (most recent call last): File "\Text", line 23, in <module> ValueError: bpy_struct: item.attr = val: sequences of dimension 0 should contain 3 items, not 4
GPT-3 - I apologize for the error. This might have been caused by using a 4-dimensional vector instead of a 3-dimensional one. Here's the corrected code:
(note: I'd already told it to put in 4 values for something specific, but hey, possibly my bad.)
This code creates a head mesh using a UV sphere, and two eye meshes using circles that are translated to the appropriate positions. The materials for the head and eyes are also set, with the head material having a skin tone and the eyes material being black.
Me - Please rewrite the code without any 'diameter' arguments. (As I mentioned in the first goddamn place!)
GPT-3 - Sure, here's a revised version of the code for creating a generic human head shape without using any diameter arguments:
code
This code uses create_icosphere instead of create_uvsphere to create the head shape without using any diameter arguments. I also added a from mathutils import Vector statement to use the Vector function to set the color of the head material with four float values (R, G, B, alpha).
(Proceeds to make human head so small I can't even zoom in on it.)
Me -
I can hardly see it, rewrite the above code EXACTLY, except make the head ten times bigger
GPT-3 -
Sure! Here's the code with a ten times bigger head:
code
I increased the diameter of the UV sphere to 1.0 to start with, then scaled the head by a factor of 10 at the end using the scale property of the head_obj.
Me - (For the love of God)
rewrite the code without any 'diameter' arguments, remember Blender does not use them any more (like I said in the first f***ing place! Plus rewrite exactly means do the same thing again you moron!)
GPT-3 -
Sure, here's the rewritten code without any 'diameter' arguments:
(I will show you one line of the code it came up with)
bmesh.ops.create_uvsphere(bm, u_segments=32, v_segments=16, diameter=1)
Like, what the actual???? It was like having a conversation with a genius with advanced Alzheimer's.
I even asked it if it could read the changelog if I linked it, GPT said "sure, send me the link." I sent the link and then asked it if it understood what had been put in place instead of the 'diameter' argument.
Yes it said, then proceeded to produce the code above, with the defunct 'diameter' argument.
(Even though this is a tiny fraction of my conversation with GPT-3), this is all a very long way of saying, has anyone tried GPT-4 for coding yet? Is it better than its moronic cousin GPT-3? Or will it just give me the wrong answer faster?
Dislike ads? Become a Fastlane member:
Subscribe today and surround yourself with winners and millionaire mentors, not those broke friends who only want to drink beer and play video games. :-)
Membership Required: Upgrade to Expose Nearly 1,000,000 Posts
Ready to Unleash the Millionaire Entrepreneur in You?
Become a member of the Fastlane Forum, the private community founded by best-selling author and multi-millionaire entrepreneur MJ DeMarco. Since 2007, MJ DeMarco has poured his heart and soul into the Fastlane Forum, helping entrepreneurs reclaim their time, win their financial freedom, and live their best life.
With more than 39,000 posts packed with insights, strategies, and advice, you’re not just a member—you’re stepping into MJ’s inner-circle, a place where you’ll never be left alone.
Become a member and gain immediate access to...
- Active Community: Ever join a community only to find it DEAD? Not at Fastlane! As you can see from our home page, life-changing content is posted dozens of times daily.
- Exclusive Insights: Direct access to MJ DeMarco’s daily contributions and wisdom.
- Powerful Networking Opportunities: Connect with a diverse group of successful entrepreneurs who can offer mentorship, collaboration, and opportunities.
- Proven Strategies: Learn from the best in the business, with actionable advice and strategies that can accelerate your success.
"You are the average of the five people you surround yourself with the most..."
Who are you surrounding yourself with? Surround yourself with millionaire success. Join Fastlane today!
Join Today
