yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-12-28 07:29:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix typo in website/blog/2023-05-18-GPT-adaptive-humaneval/index.mdx (#299)

Browse Source 
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
This commit is contained in:
Surav Shrestha 2023-10-19 21:16:24 +05:45 committed by GitHub
parent 8d4afe4263
commit 1983575520
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
website/blog/2023-05-18-GPT-adaptive-humaneval/index.mdx
View File

@ -16,7 +16,7 @@ In this blog post, we will explore a creative, adaptive way of using GPT models
## Observations
* GPT-3.5-Turbo can alrady solve 40%-50% tasks. For these tasks if we never use GPT-4, we can save nearly 40-50% cost.
* GPT-3.5-Turbo can already solve 40%-50% tasks. For these tasks if we never use GPT-4, we can save nearly 40-50% cost.
* If we use the saved cost to generate more responses with GPT-4 for the remaining unsolved tasks, it is possible to solve some more of them while keeping the amortized cost down.
The obstacle of leveraging these observations is that we do not know *a priori* which tasks can be solved by the cheaper model, which tasks can be solved by the expensive model, and which tasks can be solved by paying even more to the expensive model.