Remix.run Logo
▲ InsideOutSanta an hour ago

5.6 is in no way representative, or comparable to 6.1. In fact, the 6.1 models are so good that I've just used Terra 6.1 xhigh for most tasks.

▲SOLAR_FIELDS 30 minutes ago | parent | next [-]

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

▲jpardoe 20 minutes ago | parent | next [-]

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.

▲ctbellmar 19 minutes ago | parent | prev [-]

Similar experience here. The spirals on long running tasks are out of control at times with hours going by without a conclusion.

▲SOLAR_FIELDS 16 minutes ago | parent [-]

They (OpenAI models) are very tuned to be depth first and you can coach them all you want to try to be breadth first but as that context window fills up on those long running tasks they drift back to their first principles, which means obsessively testing and verifying a singular task rather than proceeding to the next task on the list

▲quotemstr 6 minutes ago | parent [-]

If you're using a sufficiently flexible harness (perhaps your own) you can make conversations as branchy as you want.

▲mi_lk 36 minutes ago | parent | prev [-]

sol 6.1 is meh