Turns out #GPT3 can do vision too πŸ˜‰ 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 🀯

10:04 PM Β· Jul 19, 2020

59
385
74
1,746
49,387
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 πŸ˜…)
Replying to @sh_reya
GPT-3 is a great example of the β€œgarbage-in-garbage-out” 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, you’ll get intelligent outputs. (8/11)
Show this thread
2
1
1
42
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 πŸ˜‚ 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
Yooh this is awesome πŸ”₯πŸ”₯
1
0
0
0
retweetan yogi emang paling bener dah.
1
0
0
0