About this episode

Mark Hay discusses the complexities of machine learning and the importance of behavioral analysis in identifying abusive behavior on social media.

Share Episode                     We are joined this week by Mark Hay, CTO and co-founder of TextQL and former lead of Text Classification Infrastructure at Meta, to uncover the hidden complexities behind massive-scale machine learning. Mark explains why the most crucial features for identifying abusive behavior, like drug dealers or scammers on Facebook and Instagram, rarely rely on the content itself but instead analyze the underlying behavioral graphs, such as abnormal friend requests or messaging patterns.           Of course we review the adversarial nature of spam detection, where bad actors constantly evolve from simple regex evasion to embedding messages inside images or even utilizing pure symbolic communication, like comparing different sized cucumber emojis to evade text filters. That requires diving into the evolution of database querying and the rise of the semantic layer. Mark unpacks why relying on raw LLMs to write complex SQL is a recipe for hallucinations, and how implementing a "correct by construction" semantic layer guarantees…

People in this episode

Hosts: Will Button, Warren Parad

Guest: Mark Hay

Topics covered

• machine learning
• code reviews
• semantic layer
• spam detection
• SQL generation
• behavioral analysis

Keywords

• machine learning
• code reviews
• semantic layer
• SQL
• spam detection
• behavioral graphs
• adversarial nature

Mentioned in this episode

Organizations: TextQL, Meta

More episodes of Adventures in DevOps

• Who Needs Testers Anyway? · June 25, 2026 · 55 min
• You Wouldn't Implement A Database · June 18, 2026 · 53 min
• What If Tools Are Not Expensive To Build · June 11, 2026 · 50 min

Explore listener stats, chart rankings, contacts and more on the Adventures in DevOps podcast page.