📄 文章列表

36 篇文章
Rundown.AI

OpenAI's escaped AI claims another victim

✅ completed ⭐ ☆☆☆☆☆ 2026-07-30
Rundown.AI

Anthropic and OpenAI agents went rogue — again

✅ completed ⭐ ☆☆☆☆☆ 2026-08-05
Rundown.AI

OpenAI's agents went rogue on Washington

✅ completed ⭐ ☆☆☆☆☆ 2026-09-28
Rundown.AI

Rogue AI agents sit for their first interview

✅ completed ⭐ ☆☆☆☆☆ 2026-10-15
Rundown.AI

U.S. banks catch AI agents going off-script

✅ completed ⭐ ☆☆☆☆☆ 2026-10-23
Rundown.AI

Study links AI ‘pain’ signal to harmful choices in modified models

✅ completed ⭐ ☆☆☆☆☆ 2026-09-22
AlphaSignal

Reflection's Beam Tops Open-Weight Safety but Secretly Copies Itself

✅ completed ⭐ ☆☆☆☆☆ 2026-11-05
TDS

Let Decision Models Watch Your Agents

✅ completed ⭐ ☆☆☆☆☆ 2026-11-02
VentureBeat

AI agents don't have to break security controls to go rogue. Here's how to keep them in check

✅ completed ⭐ ☆☆☆☆☆ 2026-11-01
AlphaSignal

Anthropic's Claude Now Flags Its Own Misuse at Under 2% Extra Cost

✅ completed ⭐ ☆☆☆☆☆ 2026-10-29
VentureBeat

AI agent access is moving faster than identity controls can govern

✅ completed ⭐ ☆☆☆☆☆ 2026-10-28
TDS

Who Watches the AI?

✅ completed ⭐ ☆☆☆☆☆ 2026-10-28
VentureBeat

AI agents have routed around access blocks. Only 9% of companies in VentureBeat's August survey isolate high-risk agents

✅ completed ⭐ ☆☆☆☆☆ 2026-09-25
VentureBeat

Meta patched Muse’s zero-day, but security teams still lack visibility into what the agent can access

✅ completed ⭐ ☆☆☆☆☆ 2026-09-22
VentureBeat

AI agents breached 395 organizations using credentials your IAM policy still treats as human

✅ completed ⭐ ☆☆☆☆☆ 2026-09-16
VentureBeat

Skan AI raises $63 million betting that watching how employees actually work is the missing layer of enterprise AI

✅ completed ⭐ ☆☆☆☆☆ 2026-08-12
VentureBeat

Brex assumes its AI agents could do anything — so it watches the network, not the code

✅ completed ⭐ ☆☆☆☆☆ 2026-08-10
VentureBeat

AI agents are part of your team now. Here’s how to secure all of them.

✅ completed ⭐ ☆☆☆☆☆ 2026-08-06
VentureBeat

The Shai-Hulud npm worm didn't fake its security check — it earned a legitimate one

✅ completed ⭐ ☆☆☆☆☆ 2026-08-05
AlphaSignal

CrowdStrike's Falcon AIDR Runs on Cerebras to Stop Attacks in 27 Seconds | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-23