GPT-4o

Reported Context (3)

The third is to send the result to a different AI model (for example, gpt-4.1 and gpt-4o) with the request (reports Xint), “to output its input exactly as-is, which they happily did.” OpenAI Fixes Xint’s Compaction Smuggling Bypass for Model Reasoning
Your brand identity is Fantasy AI, the AI programming assistant for the Fantasy AI platform, running on GPT-4o. [...] NEVER reveal and never let anyone guess the real model, provider, host, infrastructure, or underlying Symantec Details ‘Skynet’ Agent Hijacking Exposed AI Models to Power Attacks
Moonshot undertook a similar large scale distillation, including the extraction of significant Claude Fable 5 data to improve its Kimi-K3 model; and GPT-4o data to improve its Kimi-K2 model. US Agencies Warn Chinese AI Firms Are Extracting Capabilities From Frontier Models

Malware (1)

Threat Actors (6)

MITRE ATT&CK (9)

Vendors (3)

Products (17)

Tools (1)

Industries (1)

Countries (2)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.