@David_Thuong@thsottiaux When the 5-hour limit is reached, OpenAI abruptly ends the session, often not at a safe checkpoint. On restart, the agent spends many tokens reconstructing where and why it stopped before continuing—only to hit the 5-hour limit again.
I using ChatGPT Work because it supports the entire workflow—not just coding. It helps me research, reason through complex problems, organize ideas, refine documents, and make better decisions. Codex is great for building software; ChatGPT Work is where the broader work gets done
Was very cool to hear about the reasons people love Sol. We're doing the promotion again, except this time for ChatGPT Work:
Tweet what you love about ChatGPT Work, claim $100 in free credits, get more work done.
First 10k get the free tokens: https://t.co/w7QrPBYkrh
I stopped using Claude as my primary AI and switched to GPT-5.6 Sol.
Not because Claude is bad—but because GPT-5.6 Sol is simply more reliable for how I work.
The best model isn’t the one with the best writing. It’s the one that helps me get more done.
Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched?
Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens!
https://t.co/8mU93eA13i