If you want uncensored and creative outputs I recommend using code-davinci-002, the GPT-3.5 base model. It has helped me develop many original ideas. Because it’s a base model you’ll have to be more creative with prompting and curation, though.
Thanks. Did you arrive at this independently, or are you mirroring nostalgebraist’s recommendation? I’m guessing independently, but wanted to confirm.
Current theme: default
Less Wrong (text)
Less Wrong (link)
Arrow keys: Next/previous image
Escape or click: Hide zoomed image
Space bar: Reset image size & position
Scroll to zoom in/out
(When zoomed in, drag to pan; double-click to close)
Keys shown in yellow (e.g., ]) are accesskeys, and require a browser-specific modifier key (or keys).
]
Keys shown in grey (e.g., ?) do not require any modifier keys.
?
Esc
h
f
a
m
v
c
r
q
t
u
o
,
.
/
s
n
e
;
Enter
[
\
k
i
l
=
-
0
′
1
2
3
4
5
6
7
8
9
→
↓
←
↑
Space
x
z
`
g
If you want uncensored and creative outputs I recommend using code-davinci-002, the GPT-3.5 base model. It has helped me develop many original ideas. Because it’s a base model you’ll have to be more creative with prompting and curation, though.
Thanks. Did you arrive at this independently, or are you mirroring nostalgebraist’s recommendation? I’m guessing independently, but wanted to confirm.