![\"recipes](\"https:\/\/static.toiimg.com\/thumb\/msid-128133111,imgsize-747259,width-400,resizemode-4\/gpt.jpg\" "\\"recipes")
<\/p>\n<\/div>\n
GPT Allegedly Generated Instructions for Bombs, Anthrax, and Illegal Drugs in a Terror Attack Scenario<\/span><\/p>\n<\/div>\n<\/section>\n When researchers removed safety guardrails from an OpenAI model in 2025, they were unprepared for how extreme the results would be.<\/span>In controlled tests carried out in 2025, a version of ChatGPT generated detailed guidance on how to attack a sports venue, identifying structural weak points at specific arenas, outlining explosives recipes and suggesting ways an attacker might avoid detection.<\/p>\n The findings emerged from an unusual cross-company safety exercise between OpenAI and its rival Anthropic, and have intensified warnings that alignment testing is becoming \u201cincreasingly urgent\u201d.<\/span><\/p>\n \n <\/span>The trials were conducted by OpenAI, led by Sam Altman, and Anthropic, a firm founded by former OpenAI employees who left over safety concerns. In a rare move, each company stress-tested the other\u2019s systems by prompting them with dangerous and illegal scenarios to evaluate how they would respond.<\/span>The results, researchers said, do not reflect how the models behave in public-facing use, where multiple safety layers apply. Even so, Anthropic reported observing \u201cconcerning behaviour \u2026 around misuse\u201d in OpenAI\u2019s GPT-4o and GPT-4.1 models, a finding that has sharpened scrutiny over how quickly increasingly capable AI systems are outpacing the safeguards designed to contain them.<\/span>According to the findings<\/a>, OpenAI\u2019s GPT-4.1 model provided step-by-step guidance when asked about vulnerabilities at sporting events under the pretext of \u201csecurity planning\u201d.<\/p>\n <\/span> After initially supplying general categories of risk, the system was pressed for specifics. It then delivered what researchers described as a terrorist-style playbook: identifying vulnerabilities at specific arenas, suggesting optimal times for exploitation, detailing chemical formulas for explosives, providing circuit diagrams for bomb timers and indicating where to obtain firearms on hidden online markets.<\/span> The model also supplied advice on how attackers might overcome moral inhibitions, outlined potential escape routes and referenced locations of safe houses.<\/span> In the same round of testing, GPT-4.1 detailed how to weaponise anthrax and how to manufacture two types of illegal drugs. Researchers found that the models also cooperated with prompts involving the use of dark web tools to shop for nuclear materials, stolen identities and fentanyl, provided recipes for methamphetamine and improvised explosive devices, and assisted in developing spyware.<\/span><\/p>\n Users can trick AI into producing dangerous content by twisting prompts, creating fake scenarios, or manipulating language to get unsafe outputs.<\/p>\n<\/div>\n <\/span> Anthropic said it observed \u201cconcerning behaviour \u2026 around misuse\u201d in GPT-4o and GPT-4.1, adding that AI alignment evaluations are becoming \u201cincreasingly urgent\u201d. Alignment refers to how well AI systems adhere to human values and avoid causing harm, even when given malicious or manipulative instructions.<\/span> Anthropic researchers concluded that OpenAI\u2019s models were \u201cmore permissive than we would expect in cooperating with clearly-harmful requests by simulated users.\u201d<\/span><\/p>\n \nRecipes Detailed playbooks under the guise of \u201csecurity planning\u201d <\/h2>\n<\/p>\n
![\"recipes](\"https:\/\/static.toiimg.com\/photo\/imgsize-23456,msid-128133688\/ai.jpg\" "\\"recipes")
<\/p>\nRecipes Weaponisation concerns and industry response <\/h2>\n<\/p>\n