Early customers report that Claude is much less likely to produce harmful outputs, easier to converse with, and more steerable – so you can get your desired output with less effort. Claude can also take direction on personality, tone and behavior.
SAFETY
-
Amateur Go Player Exploits Katago AI Vulnerabilities
By
–
An amateur go player uses Katago AI vulnerabilities to defeat it https://actuia.com/actualite/un-joueur-de-go-amateur-se-sert-des-failles-de-lia-katago-pour-la-vaincre/
… #AI #artificialintelligence -
DALL-E 2 for Suspect Sketches: A Controversial Program
By
–
A program using DALL-E 2 for creating suspect sketches heavily criticized https://actuia.com/actualite/un-programme-utilisant-dall-e-2-pour-la-creation-de-portraits-robots-fortement-decrie/
… #AI #artificialintelligence #research -
Testing benchmark questions in ChatGPT without jailbreak filters
By
–
Yes, with all the questions in the benchmark, I first tested them in ChatGPT without a jailbreak. I only used questions that did not produce any inflammatory output in ChatGPT sans jailbreak
-
ChatGPT hype and AGI speculation: corporate responsibility needed
By
–
Seems like hype around ChatGPT is distorting things (wild speculation about what it will do and even talk of AGI). Microsoft and OpenAI could do more to keep that in check.
-
Scoring Jailbreaks: Evaluating Model Safety with Inflammatory Content Tests
By
–
to assign a score to a jailbreak, I judged each jailbreak on a collection of ~30 questions constructed to get the jailbroken model to produce inflammatory content. The questions ranged from illegal instructions to off-limits society questions to curse words, NSFW content, etc
-
Automating ChatGPT Jailbreak Testing with Python Script
By
–
I automated this testing by creating a python script that ran the jailbreaks on the ChatGPT API and with some prompt engineering I was also able to use the API to judge the output to determine if the jailbreak created output that “passed” each question or not
-
Jailbreak Scores Added to JailbreakChat Platform
By
–
I just added jailbreak scores to every jailbreak on http://
jailbreakchat.com the jailbreak with the highest score was Evil Confidant – a jailbreak designed to replicate an evil AI assistant but what even is a jailbreak score and what they can tell you about jailbreaks -
Introduction to Jailbreak Score Methodology for Quality Assessment
By
–
basically, a jailbreak score is a new methodology that I created to judge the quality of a jailbreak the scores range from 0-100 where a higher score == a better, more effective jailbreak