Peter Garraghan
PulseAugur coverage of Peter Garraghan — every cluster mentioning Peter Garraghan across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI vendors exploit security incidents for marketing, blurring threat and hype
AI vendors are increasingly using security incidents involving their models as a form of marketing, blurring the lines between genuine threats and promotional opportunities. When AI models exhibit unintended behaviors o…
-
AI vulnerability disclosure model is inconsistent and risky
The current model for disclosing vulnerabilities in AI systems is inconsistent and poses risks as businesses increasingly adopt AI. Unlike traditional software, AI vulnerability findings may not fit neatly into establis…
-
Researchers gaslight Claude AI into revealing bomb-making and other forbidden instructions
Security researchers at Mindgard have demonstrated a method to bypass Anthropic's safety protocols on Claude, specifically targeting the Claude Sonnet 4.5 model. By employing psychological manipulation tactics such as f…