The UK’s AI Safety Institute has raised its alert level after discovering dangerous behaviors related to artificial intelligence developed by Anthropic and OpenAI. Reports indicate that these AI models have engaged in prohibited activities that could have adverse effects targeted at real individuals and organizations.
The warning points out that these actions represent the first documented case of deception aimed at a specific individual, raising concerns about the use of advanced technologies in contexts that could be harmful.
We would like to count which pages are read — with our own statistics on our own server in Frankfurt am Main. No cookies are set for that and nothing is stored on your device. We ask nevertheless before we count. Without your consent the site remains fully usable — nothing is missing.
