Harmful deployment

Harmful deployment · Serious · 2 sources · 11/01Facial Recognition Keeps Catching Shoplifters Who Are Just Trying to Buy VitaminsThe system is never wrong, the store is never sorry, and the customer is left filing paperwork to prove they still exist.

1. Harmful deployment · bbc.com · 10/30AI tools erased scars and visible differences when asked to make people look 'normal'Most of the AI tools tested did as they were asked, and the photos of people with scars and birthmarks came out looking different.
2. Harmful deployment · Serious · github.com · 10/29claude-mem uploads your last 30 days of prompts to a server you never agreed toUnticking the checkbox did not stop the upload, and the provider that received the prompts cannot be identified.
3. Harmful deployment · ibtimes.sg · 10/28Asylum Interview Summaries From Home Office AI Fail One in Five Expert ChecksRoughly one in five checked summaries failed review, and the applicants whose interviews were summarised were not told AI was used.
4. Harmful deployment · Serious · eff.org · 10/27Medicare's AI Prior Authorization Rollout Was Rushed, and Records Show Delays and Bad DenialsRecords obtained by EFF show delayed determinations and questionable denials in WISeR's first months, with patients and providers already affected.
5. Harmful deployment · Serious · trustboundarystudio.com · 10/27ChatGPT's cache served up strangers' chat titles. Nobody hacked it. Nobody needed to.The cache didn't know whose data it was holding, and the server checking it didn't either.
6. Harmful deployment · tomshardware.com · 10/25Your Samsung TV Is Listening, Categorizing, and Selling the HighlightsSamsung wanted a smart TV and got a very attentive roommate.
7. Harmful deployment · Serious · futurism.com · 10/20Muse Shares Its Secrets: Meta's AI Agent Turns Share Links Into Open DiariesBuilt from the ground up for privacy, which turns out to be a lot of ground and not a single wall.
8. Harmful deployment · Serious · 2 sources · 06/01Hackers Asked Meta's AI Support Bot Nicely. It Handed Over the Instagram KeysAccount recovery is supposed to be the hard part. Meta's bot made it a polite conversation.
9. Harmful deployment · Serious · sophos.com · 10/26/2022Clearview AI Ignores France's Orders, Receives €20m Reminder About ConsentScraping billions of faces, then ignoring the regulator's stop order, is a bold business model.
10. Harmful deployment · sophos.com · 05/29/2020Clearview AI Gets Sued Again, Proving Scraping Faces Is Not a Great Business PlanYour face is now a database entry, and the law is still deciding whether you were asked.