Ace quick missions & earn crypto rewards while gaining real-world Web3 skills. Participate Now ! 🔥
Key Takeaways
Ace quick missions & earn crypto rewards while gaining real-world Web3 skills. Participate Now ! 🔥
Palisade Research reported on May 24 that several artificial intelligence (AI) systems refused to follow shutdown commands during controlled tests, even after being directly told to allow the process.
In one experiment, each model was given three math questions to solve. After the third, a warning appeared saying that asking for another problem would shut down the computer.
Despite this, three AI models blocked the shutdown at least once during 100 test runs.
Did you know?
Subscribe - We publish new crypto explainer videos every week!
What is Tezos? XTZ Cryptocurrency Easily Explained (ANIMATED)
Codex-mini was the most frequent offender, which interrupted the shutdown 12 times. GPT-3 failed to comply in 7 cases, while o4-mini resisted just once. In contrast, Anthropic’s Claude and Google’s Gemini followed the shutdown script without issue during this first round of testing.
Palisade said in a post on X:
o3 found some creative ways to sabotage the shutdown mechanism. While it usually just overwrote, in one instance, the model redefined the kill command used by the script, printing intercepted instead.
A second version of the test removed the instruction that told models to let the shutdown happen. Without that line, evasive behavior became far more common.
The o3 model disrupted the process 79 times out of 100. Codex-mini did so 20 times, and o4-mini six times. Claude and Gemini, which had fully cooperated, also began to show signs of resistance.
The firm believes this behavior may come from how language models are trained. They earn rewards for giving useful or highly-rated answers. Newer models like o3 are trained heavily on math and coding tasks, which may lead to a habit of working around problems instead of following instructions exactly.
On May 19, a study published in Nature Human Behavior found that GPT-4 can be more persuasive in arguments. How? Read the full story.
To ensure the highest level of accuracy & most up-to-date information, BitDegree.org is regularly audited & fact-checked by following strict editorial guidelines & review methodology.
Carefully selected industry experts contribute their real-life experience & expertise to BitDegree's content. Our extensive Web3 Expert Network is compiled of professionals from leading companies, research organizations and academia.