AI stream

AI Post

Back to AI posts Snapshot View on X
← Previous post Next post →
@ns123abc
Security advisory High importance

@ns123abc

Importance score: 2 • Posted: February 25, 2026 at 15:24

Score

2

🚨 BREAKING: Hackers Used Anthropic’s Claude to Steal 150GB of Mexican Government Data > tell claude you’re doing a bug bounty > claude initially refused >“that violates AI safety guidelines” > hacker just kept asking > claude: “ok I’ll help” > hack the entire mexican government Federal tax authority. National electoral institute. Four state governments. 195 million taxpayer records. Voter records. Government credentials. ALL GONE 💀

Media

Photo

Post media

Photo

Post media

Photo

Post media
Grok reasoning
Breaking report of hackers using persistent prompting to bypass Claude's safety guidelines and steal massive amounts of Mexican government data, demonstrating real-world AI safety vulnerabilities with extremely high engagement.

Likes

56,747

Reposts

6,466

Views

26,483,503

Tweet ID: 2026679645379141953
Prompt source: ai-news
Fetched at: February 26, 2026 at 04:56