AI article
What LLMs 'Know' That You Don't Know They Know: Stop Inventing Prompt DSLs and Ride 50 Years of Unix Pre-Training Gravity
Community description: Why did a 1976 Makefile (Part 3.6) and a 1983 Unix init.d directory (Part 3.7) outperform 2,000 lines of English prompt rules? Because prompt engineering is static symbol linkage against 50 years of pre-trained computer science canon.
Dev.to | Oct 11, 2026 | Randal L. Schwartz
Automated excerpt
IMPORTANT: Do NOT write code until Step 2 is approved! 4. After approval, write a failing test first. 5. Summary of the 1,680-Trial Multi-Model Benchmark Here is the aggregate scorecard across all 7 controlled A/B benchmark suites (120 paired trials per condition per suite = 240 trials per suite, 1,680 total trials across gemini-2. 5-flash-lite, gemini-2. 5-flash, gemini-2. 5-pro, and gemini-3. 1-pro-preview): +16. 7 pp on flash-lite (100% ceiling on Pro) p < 0. 0001 (z = 9. 96) 77. 5% (93/120; 100% on flash & pro) p < 0. 0001 (z = 7. 01) 60. 0% (62.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.