Software Engineering Radio - the podcast for professional software developers SE Radio 693: Mark Williamson on AI-Assisted Debugging
Nov 6, 2025
Mark Williamson, CTO of Undo and an expert in AI-assisted debugging, dives into the transformative role of AI in debugging processes. He highlights AI's ability to analyze data, automate tedious tasks, and enhance debugging strategies. The discussion covers advanced tools like ChatDBG and time-travel debugging, which allow developers to rewind execution for deeper insights. Mark also emphasizes the benefits for developers of all experience levels and warns of potential risks, including hallucinations and security issues, stressing the importance of human oversight.
AI Snips
Chapters
Transcript
Episode notes
Debugging Is Core Development Work
- Debugging is the ongoing quest to understand what your program does and why it differs from expectation.
- Mark Williamson says most developer time is spent debugging, not writing new code.
LLMs Excel At Sifting And Automation
- LLMs help debugging mainly by sifting large data and automating tedious tasks.
- Williamson frames LLM value as finding nuggets in data and removing toil so humans can focus on understanding.
Use LLMs For Beginners And Experts
- Use LLMs both to help newcomers absorb codebase context and to speed experts through routine tasks.
- Also learn to prompt well because LLMs need high-quality context to be most useful.