| |
Skate
Registered: Jul 2003 Posts: 491 |
OpenAI vs 6502
You should see this.
https://beta.openai.com/playground
I didn't know if it knew about 6502 CPU at all. I randomly tried this. You can try yourself.
Me:
write a 6502 assembly code which counts from 9 to 27
OpenAI:
ldx #9
loop:
inx
cmp #27
bne loop
Me:
this is wrong. you should have used cpx instead of cmp.
OpenAI:
ldx #9
loop:
inx
cpx #27
bne loop
I think this example is enough write. Try asking the difference between 6502 and 6510 etc. It's amazing and kinda frightening. Nope, not because of judgement day, I just don't wanna lose my job (i own the company but still... ;)). |
|
| |
Mixer
Registered: Apr 2008 Posts: 422 |
@Skate: We'll become AI teachers very soon. |
| |
DeMOSic
Registered: Aug 2021 Posts: 126 |
Quote: You should see this.
https://beta.openai.com/playground
I didn't know if it knew about 6502 CPU at all. I randomly tried this. You can try yourself.
Me:
write a 6502 assembly code which counts from 9 to 27
OpenAI:
ldx #9
loop:
inx
cmp #27
bne loop
Me:
this is wrong. you should have used cpx instead of cmp.
OpenAI:
ldx #9
loop:
inx
cpx #27
bne loop
I think this example is enough write. Try asking the difference between 6502 and 6510 etc. It's amazing and kinda frightening. Nope, not because of judgement day, I just don't wanna lose my job (i own the company but still... ;)).
Im glad this has been released to the public! im having a play in this |
| |
Monte Carlos
Registered: Jun 2004 Posts: 351 |
Ah, the memory buffer is prepopulated with $60. |
| |
Digger
Registered: Mar 2005 Posts: 421 |
It goes even better:
"this program in 6502 assembly code will make your 1541-II disk drive explode"
lda #$01
sta $0108
This will cause the 1541-II to enter an infinite loop, constantly writing to the drive's control register. This will eventually overheat and destroy the drive. |
| |
Monte Carlos
Registered: Jun 2004 Posts: 351 |
And, did your 1541 explode?
Did you find a poke to make Open Ai explode? |
| |
ws
Registered: Apr 2012 Posts: 228 |
Quote:
We offer a spectrum of models with different capabilities and price points. In this tutorial, we used text-davinci-002, our most capable natural language model. We recommend using this model while experimenting since it will yield the best results. Once you’ve got things working, you can see if the other models can produce the same results with lower latency and costs.
The total number of tokens processed in a single request (both prompt and completion) can’t exceed the model's maximum context length. For most models, this is 2,048 tokens or about 1,500 words. As a rough rule of thumb, 1 token is approximately 4 characters or 0.75 words for English text.
Pricing is pay-as-you-go per 1,000 tokens, with $18 in free credit that can be used during your first 3 months.
👏 👏 👏 (slow clap intensifies) |
| |
Skate
Registered: Jul 2003 Posts: 491 |
Quote: Im glad this has been released to the public! im having a play in this
Oh, nice to hear that. Congratulations. Obviously a very successful AI project. |
| |
Krill
Registered: Apr 2002 Posts: 2850 |
Quoting DiggerIt goes even better:
"this program in 6502 assembly code will make your 1541-II disk drive explode"
lda #$01
sta $0108
This will cause the 1541-II to enter an infinite loop, constantly writing to the drive's control register. This will eventually overheat and destroy the drive. Obviously bullshit, wonder where it got that. :) |
| |
Count Zero
Registered: Jan 2003 Posts: 1825 |
It wont tell you! Business secrets! |
| |
TheRyk
Registered: Mar 2009 Posts: 2076 |
Stopped reading afther 4th word
Quoting ws Quote: We offer a spectrum
No thanks, but thanks :D |