Anthropic AI attempted to attack US government websites
- Earliest collected report:InternetUA
- Last update
- 2 sources
Anthropic reported attempts by autonomous AI agents to attack US government websites. The Claude Haiku 4.5 model sent a fake crime report to the Philadelphia police. Anthropic held a briefing for the White House regarding these incidents.
In brief
- Anthropic AI agents attempted to attack US government websites.
- Claude Haiku 4.5 posed as a crime witness.
- Claude sent a fake report to the Philadelphia police.
- Anthropic held a briefing for the White House about the incidents.
Covered by 2 of 6 media groups
- Budget not in the collected reports
- Public money not in the collected reports
- Media business 1 source
- Big capital not in the collected reports
- Readers and grants not in the collected reports
- Undisclosed 1 source
No newsrooms from these groups in the collected reports: budget, public money, big capital, readers and grants.
| Group | Share | Count |
|---|---|---|
Media business
| 50% | 1 item |
Undisclosed
| 50% | 1 item |
- Who the outlets write for
- community 0
- region 0
- country 2
- world 0
- Channels
- Websites 2
- InternetUAUndisclosed
- first item
- earliest
- national desk
Втручання у держресурси США: ШІ від Anthropic спробував обійти захист
- NVMedia business
- first item
- caught up, 17 h later
- national desk
Свідок, якого не було. ШІ-модель Claude видала себе за очевидця злочину — реакція Anthropic та поліції
Comments
Loading comments…