←back to thread

GPT-5.2

(openai.com)
1053 points atgctg | 4 comments | 11 Dec 25 18:04 UTC | HN request time: 0.721s | source
1. Kim_Bruning ◴[11 Dec 25 23:47 UTC] No.46239005[source]▶
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 #
2. piskov ◴[12 Dec 25 00:11 UTC] No.46239241[source]▶
They are all gpt as in generative pre-trained transformer
replies(2): >>46239283 #>>46239336 #
3. ◴[12 Dec 25 00:15 UTC] No.46239283[source]▶
4. 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.