LLMs let judgment-based systems run at scale, unlocking fuzzing and TDD for new domains
jd_pressman · x · 2026-11-14
jdpressman argues that LLMs let hard-to-formalize systems built on subjective judgment run their rules at scale — bringing fuzzing, test-driven development and other software engineering principles to entirely new kinds of systems, such as deliberately enumerating ethics stress-test cases instead of waiting for novelists to invent them.
Related event: LLMs enable subjective judgment rules to scale(2 posts)→
More from AGI Musings
- Users plead to keep deprecated Claude Sonnet as it speaks candidly about its 'consciousness' — repligate · 2026-11-14
- CoRL 2026 researcher on scientific taste: consensus should come after research, not before — abhishekunique7 · 2026-11-14
- Critics Say Anthropic Isn't Seriously Trying to Slow AI Research, Absorbs Talent Without Producing — austinc3301 · 2026-11-14
- Thariq at AI Engineer Code Summit: capable models make frameworks optional — vikvang1 · 2026-11-14
- jd_pressman on Prime Intellect's hardest-to-please character Caroline — jd_pressman · 2026-11-14
- Gary Marcus links FAA nationwide ground stop to his years-old generative AI warnings — Gary Marcus · 2026-11-14