HNHacker News
TopNewBestAskShowJobs

itbcharles

1 karma · joined September 22, 2025

submissionscomments
itbcharles··on GPT-5-Codex
So is gpt-5-codex-high better than gpt-5-high? I find it hard to believe that with half the instruction tokens a MOE model could significantly outperform, but I am certainly not knowledgable in fine-tuning.