Turns out #GPT3 can do vision too ๐Ÿ˜‰ Built an ingredient parser: take a pic of any nutrition label (google to extract text), and GPT-3 will identify ingredients, find an emoji, determine if it's unhealthy, and give a definition ๐Ÿคฏ

10:04 PM ยท Jul 19, 2020

58
387
74
1,744
49,143
to be clear, I'm not pulling from any database. And I "trained" GPT-3 using just *1* simple example
2
1
0
52
btw @sh_rey is right: much of the work here was just figuring out the right prompt (this took a while ๐Ÿ˜…)
Replying to @sh_reya
GPT-3 is a great example of the โ€œgarbage-in-garbage-outโ€ principle. If you prime poorly, you get shitty results. But since the models are probably trained on basically every piece of data on the Internet, chances are if you prime well, youโ€™ll get intelligent outputs. (8/11)
Show this thread
2
1
1
40
Replying to @lawderpaul
Oh. My. God. No. That is not how any of this works. Go home entitled tech broโ€™s.
0
0
0
0
Replying to @lawderpaul @gdb
Hmmm, GPT-3 use case is not really when you can just hardcode the list of ingredients of interests.
1
0
0
1
agreed, not to mention the info would change slightly every time ๐Ÿ˜‚ just wanted to test its ability to parse text (& threw in a couple other qs while I was at it)
0
0
0
3
Replying to @lawderpaul @ga7ahad
Cc @dtseto lol GPT-3 giving nutrition advice
0
0
0
2
Replying to @lawderpaul @gdb
@Kokodave_
1
0
0
0
Yooh this is awesome ๐Ÿ”ฅ๐Ÿ”ฅ
1
0
0
0