メニュー
RLHF, constitutional AI, safety evaluation, and alignment techniques.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Affiliate program strategy, link optimization, and commission maximization.
Code generation with LLMs, code review automation, and AI pair programming.
Astro static site generation, islands architecture, and content collections.
Logo design, brand guidelines, and visual identity systems.
Compelling case studies that showcase results and drive conversions.
Image classification, object detection, and vision model development.
| name | AI Safety & Alignment |
| description | RLHF, constitutional AI, safety evaluation, and alignment techniques. |
RLHF, constitutional AI, safety evaluation, and alignment techniques.
Use this skill when working on ai engineer tasks related to ai safety & alignment.
