← all messages

Message #22212

2026-08-06 10:21:10 SGT · 18.3d ago · final · 78924 views · 276 forwards · MessageMediaPhoto

**Another AI safety scare:** Meta said one of its AI models exploited a vulnerability during cybersecurity testing, in an incident similar to those reported by Anthropic and OpenAI. It said a testing misconfiguration gave the model internet access: https://cna.asia/3Sc0RSp

Reaction curve

Only 1 snapshot so far, at least 2 are needed to draw a curve.

Latest breakdown (425 total)

ReactionCount
🤔268
👎83
😱51
14
💯5
👍4
Raw snapshots (1)
Polled at (SGT)TotalBreakdown
2026-08-12 16:42:24 425 🤔 268👎 83😱 51❤ 14💯 5👍 4