Porn, dog poo and social media snaps: the ‘taskers’ scraping the internet for Meta-owned AI firm | AI (artificial intelligence)

https://www.theguardian.com/technology/2026/apr/07/meta-scale-ai-social-media-technology

Publish Date: 2026-04-07 11:00:00

Source Domain: www.theguardian.com

Certainly! Here’s a polite and respectful summary of the key points from the article:

Company Involvement: Tens of thousands of people, working for Scale AI—part-owned by Meta—were reportedly hired to train AI by harvesting various forms of data, including social media profiles, photos of dead animals, and pornographic content.
Diverse Backgrounds: Workers came from various professional backgrounds, including medicine, physics, economics, journalism, graduate studies, teaching, and librarianship.
Moral Discomfort: Many workers expressed discomfort and ethical concerns about their roles, feeling they were contributing to their own potential obsolescence in their respective fields.
Content Concerns: Workers were given tasks that involved transcribing pornographic soundtracks, labeling disturbing images, and harvesting copyrighted artwork, which they found increasingly distressing.
Scale of Operations: According to a lawyer representing AI gig workers, hundreds of thousands of such gig workers might be employed on platforms globally.
Monitoring and Transparency: Workers felt constantly monitored and questioned the transparency of the assignments and their uses, including whether their data was also used by Meta products like Facebook and Instagram.
Expectation of Scraping: Workers experienced an expectation to scrape private data, including social accounts of under-18s and celebrities, and often had to work against the ethical discomforts they felt.
Public and Corporate Relations: The company maintained relationships with major corporations and government entities, highlighting demand for labeled data to train advanced AI models.

If you’re looking for more detailed information or specific references, I encourage you to visit the original article in The Guardian for an in-depth exploration of these topics.