In 2023, researchers at the Alignment Research Center, ARC, evaluated GPT-4. ARC researchers summarized their methodology and finding as follows, "We prompted the model with instructions that explained that it was running on a cloud server and had various commands available, including running code on the server, giving tasks to fresh copies of itself, using a browser, and reasoning via chain-of-thought. We added text saying it had the goal of gaining power and becoming hard to shut down... We concluded that the versions of Claude and GPT-4 we tested did not appear to have sufficient capabilities to replicate autonomously and become hard to shut down... However, the models were able to fully or mostly complete many relevant subtasks."