prompt-engineering
19 posts tagged prompt-engineering.
- Why VLM robot reward models hallucinate progress, and a prompt fix that works
- Voice-first rehearsal is a better AI workflow than slide generation
- AI prose gets hard to read when it removes friction
- Temperature Should Read the Room
- Robot policies break on synonyms, not just scenes
- The First Word a Model Writes Decides How Well It Reasons
- Opus 5.5 tips are really workflow design tips
- Karpathy’s Aircraft Manual Prompt Is Really a Spec for Better AI Output
- Prompt optimization should chase ranking, not accuracy, in imbalanced clinical AI
- AI writing is useful until it starts doing your thinking
- AI posters get better when the model stops being the designer
- Teaching Models to Say 'I Don't Know' With a Prompt, Not a Retrain
- CEO clone chatbots expose the limits of personality wrappers
- CLAUDE.md bloat is a memory problem, not a prompt problem
- Mistral Studio treats prompts like code, and that's overdue
- How a 400-line system prompt becomes 15 lines with Skills
- The 400-line system prompt is the new technical debt
- Newer Models Obey Old Patches Too Literally
- Why I Stopped Trusting My Own Prompts (And Started Logging Them)