Skip to content

Stanford HAI company blog

Research shows we can only accurately identify AI writers about 50% of the time

hai.stanford.edu

Read on hai.stanford.edu → Discuss on HN (253) Archived copy

Points: 228
HN comments: 253
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Society, Policy & Culture 2023

On Hacker News

Submitted	Title on HN	Points	Comments
Mar 22, 2023	Research shows we can only accurately identify AI writers about 50% of the time by giuliomagnifico	228	253

More from Stanford HAI

All 13 posts →

Peter Norvig Joins Stanford HAI

2021469 points105 comments AI & Machine Learning details

A new book shows how the power of companies is destabilizing governance

2024333 points344 comments Tech Industry & Business details

LLMs are not greater than the sum of their parts: researchers

2023300 points266 commentscited by 5AI & Machine Learning details

Legal models hallucinate in 1 out of 6 (or more) benchmarking queries

2024215 points255 comments AI & Machine Learning details

AI agents that “self-reflect” perform better in changing environments

2023215 points43 comments AI & Machine Learning details

GenAI and erroneous medical references

2024180 points150 comments AI & Machine Learning details

Related posts from the same era

Bing: “I will not harm you unless you harm me first”

Simon Willison20233,363 points1,673 commentscited by 6 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Open source AI is the path forward

Meta Newsroom20242,360 points887 commentscited by 5 details

Building a Virtual Machine Inside ChatGPT

Jonas Degrave20222,029 points908 commentscited by 16 details

The man who killed Google Search?

Ed Zitron20241,884 points878 commentscited by 47 details

ChatGPT Plugins

OpenAI Blog20231,875 points1,106 commentscited by 14 details