Description: ChatGPT has reportedly been experiencing errors and service disruptions caused by hard-coded filters designed to prevent it from producing potentially harmful or defamatory content about certain individuals by blocking prompts containing specific names, likely related to post-training interventions. The reported names are Brian Hood, Jonathan Turley, Jonathan Zittrain, David Faber, David Mayer, and Guido Scorza.
Editor Notes: For the reference to Jonathan Turley, see Incident 506; for Brian Hood, see Incident 507. This incident also presents potential adversarial vulnerabilities, as well as unintended consequences for users sharing affected names.
Entities
View all entitiesAlleged: OpenAI and ChatGPT developed an AI system deployed by OpenAI and ChatGPT users, which harmed ChatGPT users , Jonathan Zittrain , Jonathan Turley , Guido Scorza , David Mayer , David Faber and Brian Hood.
Incident Stats
Incident ID
855
Report Count
2
Incident Date
2024-11-30
Editors
Daniel Atherton
Incident Reports
Reports Timeline
arstechnica.com · 2024
- View the original report at its source
- View the report at the Internet Archive
OpenAI's ChatGPT is more than just an AI language model with a fancy interface. It's a system consisting of a stack of AI models and content filters that make sure its outputs don't embarrass OpenAI or get the company into legal trouble whe…
nytimes.com · 2024
- View the original report at its source
- View the report at the Internet Archive
Across the final years of his life, David Mayer, a theater professor living in Manchester, England, faced the cascading consequences of an unfortunate coincidence: A dead Chechen rebel on a terror watch list had once used Mr. Mayer's name a…
Variants
A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.
Similar Incidents
Selected by our editors
/cloudfront-us-east-2.images.arcpublishing.com/reuters/56IRXWYJKRIUXF4PYIBCBMSIUY.jpg)
Did our AI mess up? Flag the unrelated incidents
Biased Sentiment Analysis
· 7 reports
Inappropriate Gmail Smart Reply Suggestions
· 22 reports
Similar Incidents
Selected by our editors
Did our AI mess up? Flag the unrelated incidents
Biased Sentiment Analysis
· 7 reports
Inappropriate Gmail Smart Reply Suggestions
· 22 reports