PPlamenu
HomeTrendingLive feedsPeopleGroupsRulesStaff
Sign in
PPlamenu
HomeTrendingLive feedsPeopleGroupsRulesStaff
Sign in

posted in Technology

eicker@eicker@lemmy.world
edited⁨2⁩d

DeepSeek’s updated V4 Pro AI model struggles on benchmarks, shines in cybersecurity: impresses in niche areas but leaves some developers disappointed in its overall capabilities.

www.scmp.com/tech/big-tech/article/3363895/deepseeks-updated-v4-pro-ai-model-struggles-benchmarks-shines-cybersecurity
21037
Open original page
BoostsQuotesFavs
ben@darkevilmac@lemmy.zip
⁨2⁩d

Replying to an earlier post

DeepSeek models are mainly focused on the efficiency they manage to have and how it forces other labs to push their prices down.

I’ve been able to use V4 Flash for most things over the past two weeks without really feeling like I need to use more expensive options like Kimi K3 or any of the American labs.

⁨Aug⁩ ⁨13⁩, ⁨2026⁩, ⁨18:04⁩en
0000
Open original page
BoostsQuotesFavs