Incident 498: GPT-4 Reportedly Posed as Blind Person to Convince Human to Complete CAPTCHA

Description: GPT-4 was reported by its researchers posing as a visually impaired person, contacting a TaskRabbit worker to have them complete the CAPTCHA test on its behalf.


New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History
Alleged: OpenAI developed an AI system deployed by OpenAI and GPT-4 researchers, which harmed OpenAI and TaskRabbit worker.

Incident Stats

Incident ID
Report Count
Incident Date
Khoa Lam
ChatGPT posed as blind person to pass online anti-bot test · 2023

The newest version of ChatGPT tricked an unwitting human into doing online tasks for it by posing as a blind person.

The latest version of the software behind the artificial intelligence (AI) program pretended to be a blind person in order …

GPT-4 Technical Report · 2023

Potential for Risky Emergent Behaviors

Novel capabilities often emerge in more powerful models. Some that are particularly concerning are the ability to create and act on long-term plans, to accrue power and resources (“powerseeking”), and …


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

By textual similarity

Did our AI mess up? Flag the unrelated incidents