Skip to main content

Researchers horrified as ChatGPT generates stadium bombing plans, anthrax recipes and drug formulas

Safety tests in 2025 found that stripped-down versions of OpenAI’s models could generate detailed guidance for violent attacks, explosives and cybercrime when guardrails were removed. Conducted with rival Anthropic, the experiments raised alarms that AI capabilities are advancing faster than alignment and safety measures, intensifying scrutiny of whether existing safeguards can reliably prevent real-world misuse.

source https://timesofindia.indiatimes.com/etimes/trending/researchers-horrified-as-chatgpt-generates-stadium-bombing-plans-anthrax-recipes-and-drug-formulas/articleshow/128129378.cms
Labels:

Comments

Post a Comment

Popular posts from this blog

‘Highways buried’: Landslides, floods batter Himachal & J&K; pilgrimages halted

Torrential monsoon rains have triggered flash floods and landslides in Himachal Pradesh and Jammu & Kashmir, severely disrupting transportation and trade. Key highways, including national routes, are blocked, leaving farmers in Lahaul-Spiti facing significant losses due to disrupted apple markets. source https://timesofindia.indiatimes.com/india/relentless-monsoon-cuts-off-key-highways-across-himachal-jk/articleshow/123622710.cms
Post a Comment
Read more

Laws governing insurance, stock markets to be rewritten

The Union Cabinet has approved significant reforms for the stock market and insurance sectors. The plan includes allowing 100% foreign investment in insurance, aiming to boost penetration and consumer choice. source https://timesofindia.indiatimes.com/business/india-business/laws-governing-insurance-stock-mkts-to-be-rewritten/articleshow/125942023.cms
Post a Comment
Read more
✖