←back to thread

DeepSeek-v3.1

(api-docs.deepseek.com)
776 points wertyk | 1 comments | 21 Aug 25 19:06 UTC | HN request time: 0.266s | source
Show context
seunosewa ◴[21 Aug 25 20:05 UTC] No.44977398[source]▶
It's a hybrid reasoning model. It's good with tool calls and doesn't think too much about everything, but it regularly uses outdated tool formats randomly instead of the standard JSON format. I guess the V3 training set has a lot of those.
replies(2): >>44977985 #>>44978742 #
1. darrinm ◴[21 Aug 25 22:14 UTC] No.44978742[source]▶
Did you try the strict (beta) function calling? https://api-docs.deepseek.com/guides/function_calling