AI & machine learning2023 · shared on Hacker News

How Language Model Hallucinations Can Snowball

Explore How Language Model Hallucinations Can Snowball, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

Read original

The conversation around the idea.

Original Hacker News threads. Different perspectives, questions, and things worth thinking about.

Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.

Links found in the discussion

Up to 50 recent source links, in HN item order.

Ytosh ·

An LLM is a lossy encyclopedia

512 points343 comments
Ylouthy ·

Hallucination is inevitable: An innate limitation of large language models

308 points474 comments
Ylambdaviking ·

A Logic for Expressing Transformers

1 points2 comments
Yheadalgorithm ·

How Language Model Hallucinations Can Snowball

1 points1 comments
Ykubami ·

Project Vend: Phase Two

1 points0 comments

One idea leads to another.

Explore more papers