Gemma 3 270M: The compact model for hyper-efficient AI

Re:Gemma 3 270M: The compact model for hyper-efficient AI by fallinditch on Thursday August 14, 2025 @04:26PM (#44905263)

> this model is not designed for complex conversational use cases

... but it's also the perfect choice for creative writing ...?

Isn't this a contradiction? How can a model be good at creative writing if it's no good at conversation?

[ Parent | on HN ]

Re:Gemma 3 270M: The compact model for hyper-efficient AI by djeastm on Thursday August 14, 2025 @05:51PM (#44906120)

I think they mean it's not designed to be able to converse with the user over long/complex topics, but it can generate fictional conversations fine.

[ Parent | on HN ]

Re:Gemma 3 270M: The compact model for hyper-efficient AI by amilios on Thursday August 14, 2025 @04:29PM (#44905296)

Not necessarily. Where do you think the overlap is between these two tasks?

[ Parent | on HN ]

Re:Gemma 3 270M: The compact model for hyper-efficient AI by fallinditch on Thursday August 14, 2025 @08:55PM (#44907496)

Good question! The overlap is a very interesting space.

Perhaps the overlap is where human input and oversight becomes valuable: in terms of veracity, trust, relevance, interestingness, etc

[ Parent | on HN ]

Re:Gemma 3 270M: The compact model for hyper-efficient AI by amilios on Friday August 15, 2025 @11:50AM (#44913864)

Yeah, I guess "creative writing" in this case is a shortcut for essentially saying they aren't that good at conforming to user-specified constraints. They can generate "creative" texts but can't necessarily constrain and iterate on their output in a conversational setting effectively.

[ Parent | on HN ]