Classifying 1,018 AI research papers with Jev cost $0.08 total at 256ms median latency
With DeepSeek V4 Flash handling summaries first and Jev picking from 24 topics, all for just over $4 of inference.
DeepSeek v4.1 Flash created this using only code
Time for another Friday round up of useful AI tooling for designers and builders...
The theme this week is constraints. For a while we were wondering whether a model could generate a good UI. See the video below from MSchwaibold, all created with Astra from his taste/direction.
No API keys, no setup
Puts 4 open models in 1 picker Kimi K3 + DeepSeek V4 Pro, one click up to 50x usage on GLM 5.3 Flash (user 50x usage in 24hrs) 11M+ Bolt users and vide coders reading this:
You have reached the end of the archive
All of deepseek