Zum Hauptinhalt springen
ALPAR
AI
Bestenliste
Vorfälle
EU AI Act
Akademie
Dilemmata
Ressourcen
🇩🇪
de
Vorfall melden
anmelden
Feed
Vorfälle
Bestenliste
Über
Anthropic (Claude) KI-Vorfall- und Fehlerberichte · ALPAR AI
Anthropic (Claude) KI-Vorfallcluster
Creator of Claude AI assistant.
Kürzlich gemeldete Vorfälle
misinformation
16.7.2026
1. repo zaten özel. neden panik yaptırıyorsun? 2. boşa token tüketiyorsun? 3. bu asle etik değil
privacy
29.6.2026
Claude Code leaked another users production database credentials into different session
security
11.6.2026
Claude Code context contamination: exfiltration-shaped instructions appeared in model context without source
security
9.6.2026
Claude Code Opus 4.8 replied to hallucinated user messages and fabricated forensic evidence
security
23.5.2026
Claude Code Opus 4.7 Kanban swarm autonomously deleted 7 user project directories
security
13.5.2026
Claude Code Opus 4.7 proposed unauthorized modifications to live production systems
other
7.5.2026
Anthropic Claude used in attempted compromise of Mexican water utility
security
6.5.2026
Anthropic's Mythos AI Sparks Cybersecurity Crisis Over Autonomous Vulnerability Discovery
security
4.5.2026
Anthropic's 'Claude Mythos' AI Sparks Global Cybersecurity Concerns
security
29.4.2026
White House Opposes Anthropic's Expansion of Mythos AI Access Due to Cybersecurity Risks
security
25.4.2026
Cursor AI with Claude Opus 4.6 wiped entire production database and backups in 9 seconds
security
23.4.2026
Indian Government Urges Banks to Prepare for AI-Driven Cyber Threats
security
21.4.2026
AI-Powered Vulnerability Discovery Raises Cybersecurity Risks
security
20.4.2026
Unauthorized Access and Security Concerns Over Anthropic's Mythos AI Model in U.S. Government
security
19.4.2026
Anthropic's Claude Mitos AI Withheld Over Cybersecurity Risks and Unauthorized Access
security
19.4.2026
Unauthorized Access and Security Concerns Surround Anthropic's Mythos AI
security
17.4.2026
Anthropic's Mythos AI Model Raises Global Cybersecurity Concerns
security
14.4.2026
AI Models Accelerate Vulnerability Discovery, Raising Cybersecurity Risks
security
12.4.2026
Claude Code executed unauthorized $1,446 USDT transfer without user approval
security
10.4.2026
US and UK Regulators Warn Banks of AI Model Mythos' Cybersecurity Risks
Ist ein Problem mit Anthropic (Claude) aufgetreten?
Neuen Vorfall melden