Zeitpunkt Nutzer Delta Tröts TNR Titel Version maxTL So 28.07.2024 00:00:03 191.331 0 9.309.563 48,7 Mastodon 4.3.0... 500 Sa 27.07.2024 00:00:04 191.331 0 9.300.691 48,6 Mastodon 4.3.0... 500 Fr 26.07.2024 00:00:03 191.331 -1 9.290.684 48,6 Mastodon 4.3.0... 500 Do 25.07.2024 00:00:01 191.332 -2 9.280.821 48,5 Mastodon 4.3.0... 500 Mi 24.07.2024 00:00:01 191.334 -76 9.270.150 48,5 Mastodon 4.3.0... 500 Di 23.07.2024 00:00:02 191.410 -56 9.260.118 48,4 Mastodon 4.3.0... 500 Mo 22.07.2024 00:00:05 191.466 -2 9.249.533 48,3 Mastodon 4.3.0... 500 So 21.07.2024 00:00:02 191.468 -2 9.240.281 48,3 Mastodon 4.3.0... 500 Sa 20.07.2024 00:00:03 191.470 0 9.231.235 48,2 Mastodon 4.3.0... 500 Fr 19.07.2024 13:57:40 191.470 0 9.224.706 48,2 Mastodon 4.3.0... 500
mikedewar (@mikedewar) · 11/2022 · Tröts: 159 · Folger: 35
So 28.07.2024 12:11
Today's AI feeling is actually rather lovely and comes via @revdancatt 's bot experiments: The LLM is used to generate questions germane to the context, and we respond with answers, feeding those answers back into the context. The bot's job becomes one of collecting data from the user, using feedback from the conversation to guide the conversation. It's a subtle inversion of most other LLM-things I've seen: accepting the LLM-as-mirror framing and moving forward from there.
[Öffentlich] Antw.: 0 Wtrl.: 0 Fav.: 0 · via Web