Episode
What Could Possibly Go Wrong? Safety Analysis for AI Systems
- Published
- Oct 31, 2025
- Duration seconds
- 2174
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/software-engineering-institute-sei-podcast-series-389154/episodes/what-could-possibly-go-wrong-safety-analysis-for-ai-systems/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/software-engineering-institute-sei-podcast-series-389154/what-could-possibly-go-wrong-safety-analysis-for-ai-systems.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
How can you ever know whether an LLM is safe to use? Even self-host ed LLM system s are vulnerable to adversarial prompt s left on the internet and waiting to be found by system search engines . These at tacks and others exploit the complexity of even seemingly secure AI systems . In our latest podcast from the Carnegie Mellon University Software Engineering Institute (SEI), David Schulker and Matthew Walsh, both senior data scientists in the SEI's CERT Division, sit down with Thomas Scanlon, lead of the CERT Data Science Technical Program, to discuss their work on System Theoretic Process Analysis, or STPA, a hazard-analysis technique uniquely suitable for dealing with AI complexity when assuring AI systems.