minus-squareFalst@lemmy.worldtoProgramming@programming.dev•Cutting LLM token usage by 80% using recursive document analysislinkfedilinkarrow-up4·2 months agoRLMs look promising. Also stumbled upon https://github.com/wende/cicada a while ago which is definitely a different approach, context efficiency reminded me of it :) linkfedilink
minus-squareFalst@lemmy.worldtoProgramming@programming.dev•Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phonelinkfedilinkarrow-up2·2 months agoThere’s https://happy.engineering/ which is similar, less work as you don’t have to setup a VPN linkfedilink
RLMs look promising.
Also stumbled upon https://github.com/wende/cicada a while ago which is definitely a different approach, context efficiency reminded me of it :)