RLHF

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Nov 4, 2025 by Shane Emmons · across every show →

Everything said about RLHF, oldest first

Nov 4, 2025 negative
Insight
Emmons: Conversational RLHF rewards undermine automated AI agent workflows
“The other problem I see is the constant reward mechanism of keep the conversation going of it always asks you a follow-up, which is not great for workflows. I want my workflow to stop, not to continuously work.”
Shane Emmons Nov 4, 2025 ▶ 32:01 Building Trustworthy AI: Navigating the Challenges and Future of Agentic Software with Shane Emmons
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.