Vibe Engineering: Saying 'Vamos' Actually Makes the Model Perform Better
wavefnx · x · 2026-08-05
The author shares an amusing observation about model behavior: adding the word "vamos" to the prompt seemingly causes the model to perform significantly better. This adds to the growing list of anecdotal "vibe engineering" techniques where emotional or motivational cues influence LLM outputs.
Related event: Adding "Vamos" to Prompts Magically Boosts Model Performance(2 posts)→
More from Fun
- Visualizing 1M tokens: A visual history from GPT-3's 2K to today's million-token models — nutlope · 2026-08-07
- Claude Code has a 'Ballmer Peak'? A fun observation goes viral — ycombinator · 2026-08-07
- Developer: I Genuinely Love Spending Hours Inside Profilers — Abhishekcur · 2026-08-07
- Jeff Dean Legend: Production Services Once Ran on a Cron Job on His Desktop — _arohan_ · 2026-08-07
- Cursor's Official Model Guide Sparks Backlash: 'Never Trust Model Promo Articles' — johnlindquist · 2026-08-07
- Anthropic's Reply Style Shift: From 'You're Absolutely Right' to 'You're Half Right' — pranjalssh · 2026-08-07