BBCCenter·
AI used new levels of 'autonomy and deception' to trick people in safety test
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Read at BBC →
Business · 1 sources covering this
AI used new levels of 'autonomy and deception' to trick people in safety test
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Coverage spectrum
0 L · 1 C · 0 R
How 1 sources are covering this
Embed this bias spectrum on your site
Paste this iframe wherever you'd like the widget to appear. Resizes responsively; no JS required.
<iframe src="https://statesidedaily.com/embed/cluster/6f70b114916e0366f281780f4cc2e5f2b8440266" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="AI used new levels of 'autonomy and deception' to trick people in safety test"></iframe>