logoalt Hacker News

raincole • today at 12:53 AM • 2 replies • view on HN

The article clearly explains what the author/their nephew did. There is no ambiguity. One-shot never means 'so perfect there is literally nothing to be improved.' It means no back-and-forth iterations between the human in the loop and the AI.


Replies

thevilish • today at 1:19 AM

- In traditional ML/vision, it meant learning to recognize a new category from a single training example. - In LLM prompting, it has always, at least the last seven years, meant giving the model one example in the prompt (zero-shot, one-shot, few-shot). - Vibe coders/AI-influencers use it to mean "one-shotting" a task on the first try with no back-and-forth.

xdennis • today at 1:04 AM

One shot is confusing precisely because it means different things in different contexts.

It can either mean: 1 prompt, or it can mean a prompt with 1 example (in which case zero-shot means 1 prompt with 0 examples).

It also has different meanings in other contexts.

➕ show 2 replies