Ziwen Profile
Ziwen

@ziwen_h

Followers
43
Following
15
Media
3
Statuses
13

@UofT student interested in all things #AI #ML

Toronto, Canada
Joined November 2022
Don't wanna be here? Send us removal request.
@ziwen_h
Ziwen
3 years
RT @karpathy: One of my favorite results in 2022 was that it's not enough to just think step by step. You must also make sure to get the ri….
0
187
0
@ziwen_h
Ziwen
3 years
RT @newscientist: Getting good answers from an artificial intelligence can be tricky, and now researchers have found that an AI is better a….
Tweet card summary image
newscientist.com
Getting good answers from an artificial intelligence can be a tricky task, and now researchers have found that an AI is better at asking questions of another AI than people are
0
7
0
@grok
Grok
4 days
Join millions who have switched to Grok.
178
363
3K
@ziwen_h
Ziwen
3 years
RT @michaelrzhang: Neat result from applying automated prompt generation on translation. Referencing "Google Translate" in the prompt impro….
0
2
0
@ziwen_h
Ziwen
3 years
RT @Yongchao_Zhou_: Try out our Automatic Prompt Engineering (APE) Studio on your use cases. Tweet us your amazing prompts!. GUI: https://t….
0
6
0
@ziwen_h
Ziwen
3 years
Invest in APE. A couple dollars of overhead means huge savings amortized over the lifetime of inferences – by far more token efficient than in-context learning. (3/3)
Tweet media one
0
0
4
@ziwen_h
Ziwen
3 years
Why was it cheaper to generate instructions with more expensive models? Conciseness. (2/3)
Tweet media one
1
0
2
@ziwen_h
Ziwen
3 years
What’s the best bang for the buck with APE? We perform a cost analysis by generating instructions with different models. (1/3)
Tweet media one
@keirp1
Keiran Paster
3 years
Can large language models write prompts…for themselves? Yes, at a human-level (!) if they are given the ability to experiment and see what works. with @Yongchao_Zhou_, @_AndreiMuresanu, @ziwen_h, @silviupitis, @SirrahChan, and @jimmybajimmyba .(1/7)
1
3
8
@ziwen_h
Ziwen
3 years
RT @nearcyan: Large Language Models Are Human-Level Prompt Engineers. "Inspired by the human approach to prompt engineering . we ach….
0
59
0
@ziwen_h
Ziwen
3 years
RT @shaneguML: “Let’s work this out in a step by step way to be sure we have the right answer” is now on the leaderboard!.
0
8
0
@ziwen_h
Ziwen
3 years
RT @_akhaliq: Large Language Models Are Human-Level Prompt Engineers.abs: .project page: ht….
0
49
0
@ziwen_h
Ziwen
3 years
RT @keirp1: Searching for the right prompt? APE makes it easy to find a prompt that works for your language modeling task. Try our official….
0
8
0
@ziwen_h
Ziwen
3 years
RT @keirp1: Can large language models write prompts…for themselves? Yes, at a human-level (!) if they are given the ability to experiment a….
0
108
0