EmBench

This post was originally publcijed on Hackernoon, Spet 19th, 2024. OpenAI o1 came out just in time for me to add it to my 2024 Q3 benchmarks on AI empathy (to be published next week). The results for...

When you Google "artificial intelligence and empathy" there are a number of articles and opinion pieces about the dangers of artificial empathy. What is less discussed are the benefits.  As a psychologist...

Introduction This post is a follow-up to Testing the Depths of AI Empathy: You Decide! (also publish on Hackernoon as Can Machines Really Understand Your Feelings? Evaluating Large Language Models for...

Introduction Have you really thought about empathy? What does empathy mean to you? Is your ability to judge empathy different from your ability to be empathetic? This article will challenge you to consider...

For several months https://embench.com has been tracking the empathetic capability of AI models and apps. Although it has not yet published the results, EmBench has already tested ChatGPT 4o. This testing...

After my posting regarding Hume, people reached out and asked for a similar comparison with Pi.ai. I was also asked to cover more scenarios and longer scenarios. Regarding the more scenarios, it is effectively...

Shortly after I finished writing Testing the Extents of AI Empathy: A Nightmare Scenario, I came across the funding announcement for Hume. The last time I visited their site a few months ago, they did...

First, I'll acknowledge the clickbait. In this article I discuss how AIs respond to users saying they have nightmares. This is not an article about the AI Apocalypse. My previous posts have been process...

The benchmarks in this article are the results of testing the empathetic capability of generative AI models using standard psychological and purpose built measures. Prior to presenting and analyzing the...