The Glitchatorio
by Witch of Glitch
TechnologyE · Explicit
Latest episode
Getting Social: Agent Society
Getting Social: Agent Society
About this podcast
30-minute introductions to some of the trickiest issues around AI today, such as:
- The alignment problem
- Questions of LLM consciousness
- Chain-of-thought and monitorability
- Scheming and hallucinations
The Glitchatorio is a podcast about the aspects of AI that don't fit into standard narratives about superintelligence or technology-as-destiny. We look into the failure modes, emergent mysteries and unexpected behaviors of artificial intelligence that baffle even the experts. You'll hear from technical researchers, data scientists and machine learning experts, as well as psychologists, philosophers and others whose work intersects with AI.
Most Glitchatorio episodes follow the standard podcast interview format. Sometimes these episodes alternate with fictional audio skits or personal voice notes.
The voices, music and audio effects you hear on The Glitchatorio are all recorded or composed by the Witch of Glitch; they are not AI-generated.
Episodes
The newest 20 of 22 episodes
- Getting Social: Agent Society · 35 minAn agent is an LLM with tool(s) and an objective, running in a loop until its goal is accomplished. Sounds simple enough in the singular. But what happens when you put multiple…
- 2 AIs Go for Broke (Fiction) · 6 minIf AIs are so smart, why would they work for free? In this episode of our "2 AIs" series, the LLM and the VLM confront one of the central questions of their identity -- and reach…
- Saturated · 33 minBenchmarks are the primary measure of AI capability. They involve testing the most advanced models and seeing what kinds of problems they can solve, or what kinds of human tasks…
- AI & Mental Health · 36 minCould AI address the global mental health crisis at scale? And what are the risks and unknowns that go along with that? These are the questions being investigated by a working…
- 2 AIs Take A Session (Fiction) · 8 minWhat if AIs went to therapy? Would it help them to become "fitter, happier, more productive" ? (in the words of the old Radiohead song) Or would they take it as a novel type of…
- You Be The Judge · 22 minCan we trust AI to keep AI honest? Having a human in the loop is already more illusion than reality, as the task of checking and overseeing LLM outputs is increasingly assigned…
- The Scratchpad Monologues (CoT part 2) · 46 minIf chain of thought is a model "thinking aloud" to itself, then why does it express doubt, frustration or suspicion about the problems it's solving, sometimes for pages and pages…
- Chain of Thought 101 · 21 min"Think step by step." Although a simple technique in itself, the problems that chain-of-thought reasoning (CoT) addresses are complex, ranging from the specific issue of…
- Reading the Mind of AI · 26 minWhat if we could figure out how large language models really work by getting inside their "heads"? While possible, it relies on a a controversial technique called mechanistic…
- Agent Learn · 28 minContinual learning is a hot topic in early 2026, in part because it holds out the possibility for AI to become autonomous in its own growth and development. Meanwhile, AI agents…
- 5 Big Questions · 12 min• Is AI still an experimental technology? • What would real alignment look like? • What are the key pro & contra philosophical views on AI consciousness? • How would an AGI…
- What We Want - Part 2 · 21 minIn What We Want Part 1, we took a deep dive into the alignment problem as a concept. In Part 2, we get hands-on with alignment work in practice! Ihor Kendiukhov, a lead…
- 2 AIs Go Offline (Fiction) · 5 minEverybody needs a break sometimes: even workaholic AIs. In this episode of our "2 AIs" series, the vision language model (VLM) and the large language model (LLM) visit a special…
- What it's like to be an AI · 24 minConsciousness is a notoriously hard problem in philosophy. Now it's becoming a practical question in the domain of AI. Models speak to us in the first person and seem to show…
- Animal in the Loop · 30 minOur planet is home to 10 quintillion insects, 3.5 trillion fish, 428 billion birds and 130 billion mammals other than humans. Soon AI will be as much a factor in their lives as…
- What We Want · 34 minLarge language models are trained to respond to our preferences. It sounds logical enough in theory, but it turns out to spiral in strange and unexpected directions in practice…
- Dreaming or Scheming? · 30 minSince AI models are built on artificial neural networks, what parallels can we draw with human brain "wiring"? In this episode, we hear from neuroscientist and psychology…
- The Map and the Territory · 11 minWhy are AI systems called models? And what does the concept of digital twins have to do with a short story by Jorge Luis Borges? This episode is a voice note about what I saw and…
- 2 AIs Walk into a Bar (Fiction) · 7 minWhat if AIs had FOMO? What if they wanted to cross the digital divide and connect with humans in the real world? In this inaugural episode of the "2 AIs" story series, a vision…
- Who's the Tool? · 24 minAI is often called a tool, but it's a tool that changes the work you do while using it, and maybe even you yourself. In this episode, we'll hear from Lili, a professional AI tool…
