AI Code Hallucinations Increase the Risk of 'Package Confusion' Attacks - WIRED
A new study found that code generated by AI is more likely to contain made-up information that can be used to trick software into interacting with ...
Read the original at wired.com ↗
- Topics
- Hallucinations & Fabrication
- Tracked via
- “AI Risks”
Same story, other outlets
- AI Code Hallucinations Increase the Risk of 'Package Confusion' Attacks - WIRED WIRED · May 01, 2025