News for hackers. Stuff that matters.
Re:Speed up responses with fast mode by legojoey17 on Saturday February 07, 2026 @08:15PM (#46930323)
What's crazy is the pricing difference given that OpenAI recently reduced latency on some models with no price change - https://x.com/OpenAIDevs/status/2018838297221726482
Re:Speed up responses with fast mode by dcre on Saturday February 07, 2026 @08:49PM (#46930538)
Yes, but GPT-5.2 and Codex were widely considered slower than Opus before that. They still feel very slow, at least on high. I should give medium a try more often.