Wow, the 2.5 Pro summary is *far* better, it reads like coherent English instead... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jiggawatts 5 months ago \| parent \| context \| favorite \| on: GPT-5 Wow, the 2.5 Pro summary is far better, it reads like coherent English instead of a list of bullet points.

mustaphah 5 months ago | [–]

Someone should start a Gemini-powered blog that distills the top HN posts into concise summaries.

primaprashant 5 months ago | [–]

yes, agreed. Context length might be playing a factor as total number of prompt tokens is >120k. Performance of LLMs generally degrade at higher context length.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact