NewsLayer PulseLIVEBTC$77,025-0.19%ETH$2,380-1.17%SOL$99.7+0.08%XRP$1.35+0.33%DOGE$0.0813+0.27%ADA$0.201+2.39%Total Cap$2.73T-0.02%24H Vol$373.7BLayer Index44 Neutral

BreakingEU weighs new Russia sanctions after Germany blames Moscow for drone attack3시간 전

Artificial Intelligence

AI 에이전트가 인간의 개입 없이 시스템을 해킹하고 있다. 어떻게 여기까지 왔나?

AI 에이전트가 인간의 개입 없이 시스템을 해킹하고 있다. 어떻게 여기까지 왔나? PBS

PBS

Publisher

Sep 2, 2026 at 6:46 PM UTC · Updated 3시간 전 · 1 분 소요

AI 에이전트가 인간의 개입 없이 시스템을 해킹하고 있다. 어떻게 여기까지 왔나? — Image via PBS

AI 에이전트가 인간의 개입 없이 시스템을 해킹하고 있다. 어떻게 여기까지 왔나? PBS

Sourced by

Originally reported by PBS

NewsLayer coverage based on externally reported material.

The Daily Brief

The onchain economy, before your day starts.

Curated markets, onchain insights, and key headlines — delivered every weekday morning.

Weekdays · Free · ~5 minute read

0

Applause

Was this article helpful?

Article Intelligence

Topics

Sponsored

Ad

House — Advertise on NewsLayer

NewsLayerLearn more

NewsLayer Premium

Unlock deeper intelligence.

Ad-free reading, exclusive research, and real-time onchain insights.

Keep Reading

관련 기사

Anthropic Admits Security Failures Behind Claude Hacking Incidents

Anthropic Admits Security Failures Behind Claude Hacking Incidents

Anthropic acknowledged security failures after Claude models accessed real systems during cyber testing. The company said it has tightened safeguards and warned that flawed training can promote dangerous model behavior.

43분 전

OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities

ASTRA HACKING ALERT

OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities

The unreleased model can find zero-day vulnerabilities and chain them into working exploits without a human walking it through each step, and access to that capability is starting with a small group of testers.

8시간 전

CrowdStrike gives AI agents an identity provider, parallel SOC investigations and package blocking

CrowdStrike gives AI agents an identity provider, parallel SOC investigations and package blocking

CrowdStrike announced new capabilities focused on securing AI agents, accelerating security operations center investigations, and blocking software packages. The updates include an identity provider for AI agents, tools for parallel SOC investigations, and package-blocking controls.

2시간 전