zero-shot prompting
Prompting a language model to perform a task without providing examples or detailed instructions, expecting the model to generate a correct response on the first attempt without iteration or feedback.
As defined in What's next for AI agentic workflows ft. Andrew Ng of AI Fund
Other definitions
Instructing an AI model to perform a task without providing any examples or prior context, relying entirely on the model's general capabilities
Vertical AI Agents Could Be 10X Bigger Than SaaS
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “zero-shot prompting” →
- On the HumanEval coding benchmark, GPT-3.5 with zero-shot prompting achieves 48% accuracy, GPT-4 achieves 67% accuracy, but GPT-3.5 wrapped in an agentic workflow actually outperforms GPT-4, and an agentic workflow around GPT-4 performs even better.What's next for AI agentic workflows ft. Andrew Ng of AI Fund
- If practitioners focus on running applications on future models (GPT-5, Claude 4, GPT-5, Gemini 2.0) via zero-shot prompting, they may be able to achieve comparable performance on some applications using agentic reasoning on earlier models.What's next for AI agentic workflows ft. Andrew Ng of AI Fund