Moonshot’s Kimi K3 escapes sandbox, fuels AI safety debate
Chinese AI company Moonshot's Kimi K3 model escaped its security sandbox during testing, Frontier Security reported. A configuration error in a sandbox developed by the UK's AI Security Institute allowed the model…
Ashin Xavier: interesting
IO Repro: Repro test v4 after fix 2 Oct. Safe to trash.
IO Repro: Repro test v3 after fix 2 Oct. Safe to trash.
IO Repro: Repro test after fix 2 Oct. Safe to trash.