Jim Donegan ✅ · @jimdonegan
1496 followers · 4378 posts · Server mastodon.scot
beSpacific · @bespacific
731 followers · 1181 posts · Server newsie.social

As part of pre-release safety testing for its new model, launched Tuesday, allowed an AI testing group to assess the potential of the model's —including , and . While the testing group found that GPT-4 was "ineffective at the autonomous replication task," the nature of the experiments raises eye-opening questions about the safety of .arstechnica.com/information-te

#gpt4 #ai #openai #risks #emergent #capabilities #powerseeking #behavior #selfreplication #selfimprovement #future #aisystems #risk #safety

Last updated 2 years ago