phowell
/
pocketflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Zachary Huang 2025-03-20 21:04:36 -04:00 committed by GitHub
parent a013f6337a
commit 269f6c844a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
cookbook/pocketflow-thinking/README.md
View File

@ -64,8 +64,10 @@ This problem demonstrates why extended thinking is valuable:
For comparison: For comparison:
- [Claude 3.7 Sonnet (without thinking)](https://claude.ai/share/31bf938c-94dd-42f6-bfac-e82ba3616dbc): Wrong answer - [Claude 3.7 Sonnet (without thinking)](https://claude.ai/share/31bf938c-94dd-42f6-bfac-e82ba3616dbc): Wrong answer
- [GPT-4o with thinking](https://chatgpt.com/share/67dcb1bf-ceb0-8000-823a-8ce894032e37): Correct answer after 1.5 min
- [Claude 3.7 Sonnet with thinking](https://claude.ai/share/0863f9fd-ae75-4a0c-84ee-f7443d2fcf4a): Correct answer after 4.5 min - [Claude 3.7 Sonnet with thinking](https://claude.ai/share/0863f9fd-ae75-4a0c-84ee-f7443d2fcf4a): Correct answer after 4.5 min
- [GPT-o1 with thinking](https://chatgpt.com/c/67dcbad0-75c8-8000-a538-ee6df8083832): Correct answer after 0.5 min
- [GPT-o1 pro with thinking](https://chatgpt.com/share/67dcb1bf-ceb0-8000-823a-8ce894032e37): Correct answer after 1.5 min
Below is an example of how Claude 3.7 Sonnet uses thinking mode to solve this complex problem, and get the correct result: Below is an example of how Claude 3.7 Sonnet uses thinking mode to solve this complex problem, and get the correct result:
@ -344,4 +346,4 @@ Therefore, the probability of forming a triangle is 2ln(2) - 1, which is approxi
====================== ======================
``` ```
> Note: Even with thinking mode, models don't always get the right answer, but their accuracy significantly improves on complex reasoning tasks. > Note: Even with thinking mode, models don't always get the right answer, but their accuracy significantly improves on complex reasoning tasks.