Category Not Found

1252 prompts

Sort:

Reduce accuracy on research synthesis Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a research synthesis prompt on Qwen 2.5 72B against accuracy without regressing safety.

Reduce F1 score on scientific literature review Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a scientific literature review prompt on Gemini 2.0 Flash against F1 score without regressing safety.

Reduce F1 score on bug root-cause analysis Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a bug root-cause analysis prompt on GPT-4o-mini against F1 score without regressing safety.

Reduce F1 score on incident post-mortems Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a incident post-mortems prompt on o1-mini against F1 score without regressing safety.

Reduce factuality on technical spec writing Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a technical spec writing prompt on DeepSeek-V3 against factuality without regressing safety.

Reduce factuality on schema migration planning Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a schema migration planning prompt on Claude 3.5 Sonnet against factuality without regressing safety.

Reduce refusal rate on funnel analysis Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a funnel analysis prompt on o3 against refusal rate without regressing safety.

Reduce refusal rate on resume screening Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a resume screening prompt on DeepSeek-R1 against refusal rate without regressing safety.

Reduce toolcall precision on code generation Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a code generation prompt on Claude 4 Sonnet against toolcall precision without regressing safety.

Reduce toolcall precision on multi-hop QA Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a multi-hop QA prompt on o3-mini against toolcall precision without regressing safety.

Reduce format-compliance rate on medical triage Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a medical triage prompt on Llama 3.1 405B against format-compliance rate without regressing safety.

Reduce format-compliance rate on research synthesis Prompt via Textual Gradient Descent

Use Textual Gradient Descent to optimize a research synthesis prompt on Claude 4.5 Sonnet against format-compliance rate without regressing safety.

💬ChatGPT

386638