News for hackers. Stuff that matters.

A comment on GPT-5: Overdue, overhyped and underwhelming. And that's not the worst of it. Parent comment

Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by mikert89 on Saturday August 09, 2025 @08:56PM (#44851868)
I think it is, I've been using these models for 6 hours a day for almost a year. At any given time I have 2 of the max subscriptions (right now grok and openai).

I have a bug that was a complex interaction between backend and front end over websockets. The day before I was banging my head against the wall with o3 pro and grok heavy, gpt5 solved it first try.

I think its also true that most people arent pushing the limits on the models, and dont even really know how to correctly push the limits. Which is also why openai is not focussed on the best models

[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by I_am_tiberius on Saturday August 09, 2025 @10:14PM (#44852258)
Similar usage as me, but I don't see a difference between o3-pro and 5-pro. Sounds odd, but my impression is that o1-pro was better at creating complex independent small functions than o3-pro/5-pro.
[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by mikert89 on Saturday August 09, 2025 @10:32PM (#44852331)
Actually will agree that o1 pro was better than o3 at really deep bug finding/coding analysis. Which is also why i have the theory that they could just turn up the compute to show better results, but dont do to cost. O3 and GPT5 seem heavily quantized, o1 pro was more raw

Another thing I’ll add though, is o3 pro is better through the api than the chat website. They clearly constrain it unless you’re paying the absurd api cost

[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by I_am_tiberius on Sunday August 10, 2025 @12:45AM (#44852812)
yes, I think that's right. o1-pro for sure was too expensive for them.
[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by nojs on Saturday August 09, 2025 @10:32PM (#44852333)
How are you using GPT5 for coding (Cursor?)
[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by mikert89 on Saturday August 09, 2025 @10:39PM (#44852360)
I use repo prompt to build the prompt manually with the code files. Then give it to ChatGPT in the console. Then I have cursor ingrate the results.

I actually think cursor alone is not that good

[ Parent | on HN ]
Re:GPT-5: Overdue, overhyped and underwhelming. And that's n... by energy123 on Sunday August 10, 2025 @06:02AM (#44854086)
Has anyone noticed that OpenAI is cutting off submitted context in ChatGPT Pro?

If I send about 60k tokens, the model can't see the question (at the bottom of the text). I need to reduce it to 50k.

If I send two prompts with 40k tokens, the model can't see the beginning of the first prompt.

This seems quite unethical given they advertise 128k context, and I doubt it's an accident (since it runs in the direction of cost savings).

[ Parent | on HN ]