Episode
EP 41: The Reward Signal: The Missing Ingredient in Every AI System You’ve Built
- Podcast
- Data Science With Sam
- Published
- May 26, 2026
- Duration seconds
- 2684
- Processing state
not_requested- Canonical source
- https://rss.com/podcasts/data-science-with-sam/3006407
Actions
POST https://stenobird.com/v1/public/podcasts/data-science-with-sam-4345646/episodes/ep-41-the-reward-signal-the-missing-ingredient-in-every-ai-system-you-ve-built/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/data-science-with-sam-4345646/ep-41-the-reward-signal-the-missing-ingredient-in-every-ai-system-you-ve-built.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
74% of organizations hope to grow revenue through AI. Only 20% are actually doing it. That gap isn't a technology gap — it's a design gap. And today's guest has a name for what's missing: the reward signal. Alexander Liss is a Data and AI Scientist based in Denver, Colorado, with a 30-year career across analytics, strategy, data science, machine learning, and AI. He's built systems that solve established problems in novel ways, and the long-term problem on his radar is ensuring AI tools provide responsible augmentation of human ability. His research includes Attention Fine Tuning (AFT) - a method for training language models without human annotation labels - and the Experience Orchestrator, a control theory-based governance framework for multi-agent AI. IN THIS EPISODE: ▪ Why 95% of AI pilots fail - MIT research shows businesses bolt AI onto existing processes without tying it to real outcomes ▪ The biology analogy: hunger isn't a goal, it's a continuous feedback signal - and the same principle should govern how AI systems behave ▪ ServiceNow dynamics blindness: LLMs are stateless - they can't consider cumulative impact, and you can't prompt-engineer your way out of that architecture problem ▪ Contextual bandits in marketing: how a reward signal anchored to real conversions creates a self-learning personalisation system that adapts in real time ▪ Knowledge graphs and agent memory: why RAG retrieves answers while a reward-signal system asks what the user needs to do differently ▪ Attention Fine Tuning (AFT): a three-component reward signal (coverage, focus, repeat penalty) that trained a T5-large model to outperform a supervised fine-tuning baseline by 9% — with better multi-turn recall, and no human labels ▪ The Experience Orchestrator: aerospace control theory applied…