Comment by dcss_gardener
11 hours ago
Eh there's a lot of ways to 降智, quants are just the most visible. I noticed a fair bit of variance with opencode go and went back to deepseek direct.
11 hours ago
Eh there's a lot of ways to 降智, quants are just the most visible. I noticed a fair bit of variance with opencode go and went back to deepseek direct.
This is no longer true(?), there's zero difference between what is served by deepseek and opencode go. Infact I am pretty sure it's served by deepseek as the tok/s graphs closely align with eachother.
It's helpful that DeepSeek is so cheap that it's actually reasonable to pay standard API rates.