Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
onekq 
posted an update Sep 24
Post
2544
Here is my latest study on OpenAI🍓o1🍓.
A Case Study of Web App Coding with OpenAI Reasoning Models (2409.13773)

I wrote an easy-to-read blogpost to explain finding.
https://huggingface.co/blog/onekq/daily-software-engineering-work-reasoning-models

INSTRUCTION FOLLOWING is the key.

100% instruction following + Reasoning = new SOTA

But if the model misses or misunderstands one instruction, it can perform far worse than non-reasoning models.
In this post