Ask HN: People who switched from GPT to their own models. How was it?

88 points by ashu1461 2 years ago | 46 comments

Ask HN: How have you integrated LLMs in your development workflow?

33 points by mjbale116 2 years ago | 38 comments

Ask HN: Claude Opus performance affected by time of day?

13 points by scaredreally 9 months ago | 14 comments

Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

780 points by behnamoh 3 years ago | 631 comments

Ask HN thread where a user asks whether GPT-4's response quality has deteriorated recently, comparing ChatGPT, Phind, and Poe.

Ask HN: What are your current programming pet peeves?

15 points by alexathrowawa9 1 year ago | 37 comments

Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

474 points by superasn 1 year ago | 304 comments

Ask HN thread asking how OpenAI serves ChatGPT to 700M weekly users when a GPT-4-class model is hard to run locally, seeking inference scaling insights.