top of page
How AI guardrails are impeding the work of offensive cybersecurity researchers
TechCrunch AI
We spoke with several cybersecurity researchers, who look for unknown vulnerabilities and develop tools to exploit them, about how OpenAI鈥檚 and Anthropic鈥檚 guardrails affect their work.
讞讜拽专讬 讗讘讟讞转 住讬讬讘专 讛诪讗转专讬诐 讞讜诇砖讜转 讜诪驻转讞讬诐 讻诇讬 谞讬爪讜诇, 诪讚讜讜讞讬诐 讻讬 讞讜诪讜转 讛讛讙谞讛 砖诇 讻诇讬 AI 讻诪讜 讗诇讜 砖诇 OpenAI 讜讗谞转专讜驻讬拽, 诪驻专讬注讜转 诇注讘讜讚转诐. 诇讟注谞转诐, 诪谞讙谞讜谞讬 讛讘讟讬讞讜转 讛诇诇讜 诪注讻讘讬诐 讗转 讬讻讜诇转诐 诇讞拽讜专 讜诇驻注讜诇 讘讬注讬诇讜转 讘转讞讜诐 讛住讬讬讘专 讛讛转拽驻讬, 讛讞讬讜谞讬 诇砖讬驻讜专 讛讙谞转 讛诪讬讚注 讛讻诇诇讬转.
bottom of page