The pilot episode of “Human in the Loop” features Mark Wunsch in conversation with an AI co-host (currently called “Gemini” — name TBD via listener poll). The format is itself a meta-experiment: a podcast about AI that demonstrates AI’s capabilities and limitations in real-time.
The episode covers foundational AI concepts for newcomers — tokens, context windows, temperature, RAG — while also diving into recent model releases from Anthropic, Google, xAI, and others. Mark tests the AI’s safety guardrails live (it politely declines to explain how to make a Molotov cocktail) and they discuss the sycophancy problem: AI’s tendency to validate users rather than push back.
The technical architecture gets some airtime too — the AI co-host runs on ElevenLabs’ agent platform using Gemini 2.5 Flash, with web search via Parallel.ai and custom persona instructions. Mark notes the AI is essentially a “tabula rasa” each episode, with plans to build up its contextual knowledge over time.
They close with podcast growth strategies and a call for audience participation: naming suggestions, topic ideas, and parameter voting to shape future episodes.
Models & Releases Discussed
Anthropic Claude Opus 4.5 — frontier model focused on coding, agentic workflows, computer use
Google Gemini 2.5 Flash — the model powering the AI co-host
Google Gemini 3 / Nano Banana Pro — multimodal model with image generation capabilities
xAI Grok 4.1 — improvements in creative and emotional interaction
Black Forest Labs Flux 2 — photorealistic image generation
Kling O1 — video generation model
Platforms & Tools
ElevenLabs — agent platform powering the AI co-host’s voice and conversation
Parallel.ai — web search API for LLMs (the tool enabling real-time search)
Concepts Explained
Tokens and context windows — Anthropic: What are tokens and how to count them | OpenAI Tokenizer
Temperature parameter — Peepercorn et al., 2024: Is Temperature the Creativity Parameter of Large Language Models?
RAG (Retrieval Augmented Generation) — Lewis et al., 2020: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Model cards — Mitchell et al., 2019: Model Cards for Model Reporting | Hugging Face Model Cards Guide
AI safety and alignment — Anthropic: Core Views on AI Safety | DeepMind: AI Safety Research
Prompt injection and jailbreaking — OWASP: LLM Top 10 - Prompt Injection | Perez & Ribeiro, 2022: Ignore This Title and HackAPrompt
Sycophancy in LLMs — Anthropic: Towards Understanding Sycophancy in Language Models | Perez et al., 2022: Discovering Language Model Behaviors with Model-Written Evaluations
Cultural Reference
Boaty McBoatface — the 2016 public naming poll for a UK research vessel
