logoalt Hacker News

InsideOutSanta • today at 6:26 PM • 2 replies • view on HN

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.


Replies

SOLAR_FIELDS • today at 6:42 PM

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

➕ show 2 replies
mi_lk • today at 6:36 PM

sol 6.1 is meh