AIFinancial Times3h ago

Frontier AI labs are stepping up biological risk testing

Frontier AI labs are stepping up biological risk testing, which is harder than cybersecurity testing, where capabilities can be tested in digital environments

TL;DRAI labs are testing whether their models could help create bioweapons, a harder problem than cybersecurity.

Why it matters: AI-assisted bioweapons pose existential risks that digital safeguards can't fully address or contain.

Executives and biosecurity experts are concerned that future models could help users create novel viruses or bioweapons.

Read full article

Source: Financial Times · Opens in new tab