(openai.com)

1019 points atgctg | 3 comments | 11 Dec 25 18:04 UTC | HN request time: 0.438s | source

Show context

I'm continuously surprised that some people get good results out of GPT models. They sort of fail on my personal benchmarks for me.

Maybe GPT needs a different approach to prompting? (as compared to eg Claude, Gemini, or Kimi)

replies(1): >>46239241 #

1. piskov ◴[12 Dec 25 00:11 UTC] No.46239241[source]▶

They are all gpt as in generative pre-trained transformer

2. ◴[12 Dec 25 00:15 UTC] No.46239283[source]▶

3. Kim_Bruning ◴[12 Dec 25 00:21 UTC] No.46239336[source]▶

That may or may not be true, but in the context of this article, I'm referring to OpenAI's GPT brand of models.

GPT-5.2