AI models tested for spotting Amazon scams
An investigation tested three major AI assistants against 20 Amazon messages. The tools correctly identified fraudulent communications, yet only one model accepted legitimate correspondence. This highlights the current limitations in distinguishing between real and fake emails.
The results show that while AI is good at spotting fraud, it struggles with verifying legitimate messages.
Read the full coverage
- Android Police I asked Gemini, ChatGPT, and Claude to spot Amazon scams
More on: AI · Security & Privacy · #GoogleGemini · #ChatGPT · #Claude · #Amazon
This brief was written with AI from the headlines and excerpts published by the outlets above, and may contain errors. Follow the links for the original reporting.