Using LLMs to enumerate ethical fuzz tests like software engineering

jdpressman argued that LLMs could systematically enumerate ethical stress-test cases, extending software engineering methods like fuzzing and TDD to scale subjective judgment-based rule systems beyond software.

2026-11-14 ~ 2026-11-14 · 4 related posts

• jd_pressman on Prime Intellect's hardest-to-please character Caroline — jd_pressman · 2026-11-14
• Using LLMs to fuzz-test ethics systems with enumerated hypothetical characters — jd_pressman · 2026-11-14
• LLMs let judgment-based systems run at scale, unlocking fuzzing and TDD for new domains — jd_pressman · 2026-11-14
• LLMs let you run judgment-based rule systems at scale with software engineering methods — jd_pressman · 2026-11-14