Researchers claim to have hacked OpenAI using IIA Claude de Anthropic
Hacktron AI managed to access OpenAI ChatGPT accounts using an Anthropic model, revealing errors in a Discourse-managed forum.OpenAI corrected the vulnerability within 14 hours and rewarded Hacktron. The stress highlights the growing risk of food...
IntelMap indexes open-source reporting. This page identifies what a source reported; it does not independently confirm the claim.
2 reports · 2 sources
ClarínResearchers claim to have hacked OpenAI using IIA Claude de AnthropicClarínResearchers claim to have hacked OpenAI using IIA Claude de Anthropic9 recorded states
Signal first indexedP1 · 68% quality · 1 source
Corroboration 1→2 sources · quality 68→72P1 · 72% quality · 2 sources
Quality 72→76P1 · 76% quality · 2 sources
Quality 76→80P1 · 80% quality · 2 sources
Quality 80→84P1 · 84% quality · 2 sources
Quality 84→88P1 · 88% quality · 2 sources
Quality 88→92P1 · 92% quality · 2 sources
Quality 92→96P1 · 96% quality · 2 sources
Quality 96→99P1 · 99% quality · 2 sources