GPT models in my anecdotal experience are worse at drifting into the weeds on long running tasks, and continue to take what you ask way too literally. I have come to the conclusion that Anthropic’s models are just better at teasing out and intuiting what you actually mean even if you under specify it.
They are much better compute for dollar though. I have hilariously started to just have an opus thread maintain Sol subagents to get the best of both worlds
Similar experience here. The spirals on long running tasks are out of control at times with hours going by without a conclusion.
That’s exactly what I do. It’s more complex than this, but vaguely: Opus medium as orchestrator and reviewer, Sol(high/medium)/Terra(max) as implementer. My set up looks at my next GPT reset date and dynamically enters FAST mode if I’m under achieving on projected usage.