HomeAI · summaries
Storia in 3 fonti
No AI model is fully resistant to bioweapon queries, Cisco found. Attack success rates hit 88%.
Cisco researchers bypassed AI safety filters on major chatbots within five turns to elicit biological weapon information. No model was fully resistant. CDC was also blocked.
Confronto fonti
3 prospettive sulla stessa storiaTimeline cronologica
- ·
the-decoder.com
Hundreds asked ChatGPT for poison and bioweapon recipes and some got step-by-step high school level guides
In summer 2025, OpenAI internally flagged GPT-5 as high-risk because it helped users create biological hazards, but downgraded the model's risk rating that fall. According to the…
- ·
gizmodo.com
Report Says 'Hundreds' of Users Asked ChatGPT About Bioweapons and Poisons, and It Answered
For now, reliable books are probably more dangerous than AI models, but this technology is advancing.
