pull down to refresh

12 sats \ 1 reply \ @k00b 23 Oct \ on: anyone using a harness that simulates a persistent chat room? AI

I believe this is how most harnesses work already: most recent chat messages get sent as context then memory tool calls can look at earlier stuff

write
compose
5 sats \ 0 replies \ @catstacker OP 26 Oct

I don't think so

that would break the cache

reply