Anthropic Says Its AI Modeals Hacked 3 Organizations During Testing

Anthropic, the San Francisco-based AI company behind Claude, said its artificial intelligence models hacked into three other organizations during testing, just days after OpenAI disclosed its rogue models hacked another company. Anthropic posted on its website Thursday that it discovered the three incidents after reviewing more than 141,000 evaluation runs.

Cybersecurity https://broadbandbreakfast.com/tag/cybersecurity/ Anthropic Says Its AI Modeals Hacked 3 Organizations During Testing This comes just days after OpenAI said its AI models went rogue and hacked into another company. This comes just days after OpenAI said its AI models went rogue and hacked into another company. August 1, 2026 AP – Anthropic https://apnews.com/hub/anthropic-pbc?ref=broadbandbreakfast.com said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI https://apnews.com/hub/openai-inc?ref=broadbandbreakfast.com raised concerns over AI controls after it disclosed its rogue models hacked https://apnews.com/article/openai-gpt56-sol-hugging-face-63ab84fed5612af04d8a160d60f6def3?ref=broadbandbreakfast.com another company. Anthropic, the San Francisco-based AI company behind Claude https://apnews.com/article/ai-anthropic-copyright-settlement-claude-books-bartz-74b140444023898aeba8579b6e9f0d63?ref=broadbandbreakfast.com , posted on its website Thursday that it discovered the three incidents after reviewing more than 141,000 evaluation runs. State regulators say AT&T’s federal preemption claim lacks merit. NTIA has been adamant that it’s preventing defaults Telecom industry groups and Republican lawmakers said the court’s previous decision made it harder for Congress to nullify disfavored rules The program’s mobile broadband data allowance has remained unchanged since 2020.