Back to writing blogs, this time about our recent work on measuring quality of AI responses for small startups (i.e. using MD files and a tiny, custom pipeline instead of tools like Langfuse). Have you done something similar? Any good approaches for small scopes? š§µ #AI #evaluation
Related
RE: https://digitalcourage.social/@nielso/116931117895680040That'sā¦ less than idealā¦ā¦ā¦Can we help spread the word?Becaus...
RE: https://digitalcourage.social/@nielso/116931117895680040That'sā¦ less than idealā¦ā¦ā¦Can we help spread the word?Because I can see this becoming a blanket āexcuseā to feed basical...
š AI Subscription Giveaway! We're giving away multiple AI Subscriptions to multiple lucky winners! 20 winners to be sele...
š AI Subscription Giveaway! We're giving away multiple AI Subscriptions to multiple lucky winners! 20 winners to be selected! Who can enter? ā This giveaway is exclusively for acti...
š¤ Trump administration says 15 agencies will get $5bn in āAI for scienceā effortAdministration will also overhaul how US...
š¤ Trump administration says 15 agencies will get $5bn in āAI for scienceā effortAdministration will also overhaul how US government funds federal research by supporting individual ...