Tech
AI Safeguards Under Threat from Bioweapons Research
Researchers found ways to bypass safeguards in AI systems used for bioweapons research. This raises concerns about the potential misuse of advanced technology.
Coverage timeline — 2 articles
Ars Technica
Simplicity—combined with the difficulty of getting stuff done—makes ClickFix ideal.
2026-09-11 11:30 UTC
Ars Technica
Some dangerous biology looks much like legitimate research, complicating AI safeguards.
2026-09-11 13:02 UTC