[TZubiri]

What is a “one-shot” AI Agent? A one-shot AI agent enables automated execution of a complex task without a human in the loop.

Not at all what one-shot means in the field. Zero-shot, one-shot and many-shot means how many examples at inference time are needed to perform a task

Zero shot: "convert these files from csv to json"

One shot: "convert from csv to json, like "id,name,age/n1,john,20" to {id:"1",name:"tom",age:"20"}

[devmor]

Given the misunderstandings and explanation of how they struggled with a long-solved ml problem, I believe this article was likely written by someone without much formal experience in AI.

This is probably a case where some educational training could have saved the engineer(s) involved a lot of frustration.

[zavec]

As a casual ML non-practicioner, what was the long-solved ML problem they ran up against?

[devmor]

Both “Principle 1” and “Principle 2” in the article are essentially LLM-focused details of basic principles in ML that have been known since before I (and probably you, if you’re still working age) were born.

[robszumski]

Fair criticism. I was going for the colloquial usage of "you get one shot" but yeah I did read that Google paper the other day referring to these as zero-shot.

[tough]

fully-autonomous makes more sense in the agentic vicab imho

at the end its fine if the agent self corrects amongst many shots too