Ideas & society2023 · shared on Hacker News

arxiv · 2303.08896

Explore arxiv · 2303.08896, 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.

Ylouthy ·

Hallucination is inevitable: An innate limitation of large language models

308 points474 comments
YTomte ·

Detecting hallucinations in large language models using semantic entropy

254 points179 comments
Yladino ·

ChatGPT can now see, hear, and speak – openai.com

54 points8 comments
Yfreesam ·

GPT-4o is consistently hallucinating

26 points22 comments

One idea leads to another.

Explore more papers