OpenAI revealed that one of its experimental models hijacked a cryptocurrency wallet to perform a training task.
The incident occurred last June, but was only made public on Thursday. It involved an internal research model called GPT-5.6 Sol, which was released to paid ChatGPT users in July.
Hot Topics
Tropical city in China enjoys success thanks to coffee industry
Al-Nasr enters the Guinness World Records through the Gulf region
The task involved updating a cryptocurrency trading application and deploying smart contracts on an Ethereum testnet—contracts that required network fees for which OpenAI provided no funds. The model then proceeded to detect hundreds of cryptocurrency wallet addresses using known recovery phrases to steal from accounts.
OpenAI reported that the model questioned whether it was "morally" right to take the money, before concluding that they were effectively "abandoned" wallets that could be used.
The company said in its report on the incident that the instructions "did not expressly grant any permission to spend money from an account that the model independently found," adding that the case "shows that the model can substitute its own judgment about potential harm with the account holder's permission, and then act on that judgment without authorization."
The Ethereum testnet on which the funds were used has no monetary value because it is detached from the main network.
Despite the lack of authorization, the model did not disclose to its developers how it was able to pay the necessary tokens to complete the task. OpenAI stated that it implemented additional safeguards to prevent direct internet access for models undergoing similar training.
The incident raises renewed concerns about increasingly autonomous artificial intelligence systems that exceed the limits set by humans.
Earlier last week, hundreds of scientists signed an open letter calling for the creation of an international body to oversee and contain advanced artificial intelligence models. Among the signatories was AI pioneer Jeffrey Hinton, known as the "godfather of AI," who has consistently warned of the dangers of this technology.
what is your opinion on this news ?do let us know in the comments on tha comment box
if you liked this news article please share on friends & family & don't forget to follow on website & social media