Why “Zero-shot” is being discussed
The most recent Hacker News stories and comments contributing to this topic's mentions.
Finetune and infer: One instance ModernBERT didn't have the learning capacity for a single problem in the shape of my subjective preference task with finetuning, do you not have…
by BoorishBears · Sep 21, 2026
Show HN: OpenDecision – a 400M zero-shot model makes local decisions, plays Doom
by dwa3592 · Sep 21, 2026 · 6 points
You can achieve open-vocabulary classification by making the final weights in the softmax come from a category encoder instead of being fixed learned weights. So instead of soft…
by andy12_ · Sep 21, 2026
From the official report: > Since LLMs can give different answers to the same question, each question was run five times. That means, each LLM was tested 600 times, and in total…
by includenotfound · Sep 21, 2026
The concept isn't new: zero-shot classification using e.g. Facebook BART has been available for years. And there is already an open source model Laya: https://laya.con…
by niutech · Sep 20, 2026
I tried Jev a bit, and the zero-shot performance already felt good enough to be useful. If you find the right place for that tradeoff, I don’t really see why “you could fine-tun…
by mochizou · Sep 20, 2026
Interest
Proportion of Hacker News items mentioning "zero-shot" over time.
Mentions
Total number of Hacker News items mentioning "zero-shot" over time.
Zero-shot learning (ZSL) is a problem setup in machine learning where, at test time, a learner observes samples from classes which were not observed during training, and needs to predict their class. The name is a play on words based on the earlier concept of one-shot learning in computer vision, in which classification can be learned from only one example. Read more on Wikipedia