Hacker News new | ask | show | jobs
by ElFitz 4 days ago
> LLMs can only reconstitute things in its training data

Such as a 4D raytracing engine in Metal? Or integrating APIs for features first released months after their knowledge cut-off date?

LLMs have shown an ability to transfer "knowledge" and capabilities across domains, languages, and use-cases outside their training data.

Case in point: GPT-2 "learning" to translate English to French and vice versa despite non-English examples having been voluntarily (and almost entirely) removed from the dataset.
1 comments
data_maan 4 days ago
Was this in the GPT2 paper?
link
ElFitz 4 days ago
In "Language Models are Unsupervised Multitask Learners"[0]. Not sure whether it’s "the" GPT-2 paper.

3.7 Translation

> Performance on this task was surprising to us, since we deliberately removed non-English webpages from WebText as a filtering step. In order to con- firm this, we ran a byte-level language detector2 on WebText which detected only 10MB of data in the French language […]

[0]: https://cdn.openai.com/better-language-models/language_model...

link