Episode

What Could Possibly Go Wrong? Safety Analysis for AI Systems

Podcast
Software Engineering Institute (SEI) Podcast Series
Published
Oct 31, 2025
Duration seconds
2174
Processing state
not_requested
Canonical source
https://cmu-sei-podcasts.libsyn.com/what-could-possibly-go-wrong-safety-analysis-for-ai-systems
Audio
https://traffic.libsyn.com/clean/secure/cmu-sei-podcasts/STPA_Schulker_Walsh_Scanlon.mp3?dest-id=762491
JSON
/v1/public/podcasts/software-engineering-institute-sei-podcast-series-389154/episodes/what-could-possibly-go-wrong-safety-analysis-for-ai-systems
Markdown
/podcast/software-engineering-institute-sei-podcast-series-389154/what-could-possibly-go-wrong-safety-analysis-for-ai-systems.md

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.