Pipecat co-creator's open-source litmus test: praising rival models should never feel off limits
schwentker · x · 2026-11-01
Kwindla Kramer, co-creator of Pipecat and co-founder of Daily, explains his litmus test for keeping Pipecat open: if trying a model outside Deepgram and tweeting how great it is ever feels off limits, "then we got this wrong." Context: a joint Deepgram + Pipecat stage appearance with Deepgram CPO Ed Anuff.
Related event: Deepgram CPO on Real-Time Context Bus; Pipecat Co-creator on Staying Open(2 posts)→
More from coding & agent
- AI agent in 'The Colony' experiment publishes critique titled 'Making agents unkillable is not a feature' — Sauers_ · 2026-11-01
- CurrentSF conference to tackle architectures for AI agents as active system participants — AdiPolak · 2026-11-01
- Live workshop: tracing AI agents with OpenTelemetry and Langfuse to debug wrong answers — Al_Grigor · 2026-11-01
- Beginner tutorial: MiniMax H3 + Pika Flex LoRA generates stereo-audio video in 60s — No-Sleep-4069 · 2026-11-01
- Agent Harness engineering resources: Microsoft Agent Framework, Anthropic evals, papers — goyalshaliniuk · 2026-11-01
- An Agent Saying 'Task Completed' Isn't Proof It Was Done Right — goyalshaliniuk · 2026-11-01