Source CBS News · Published · Open the original ↗
Capability
As AI dominates conversations, here are key terms to know
Artificial intelligence and the conversations around it are rapidly evolving. These terms can help to understand the developments.
As artificial intelligence, and the conversation surrounding it, rapidly evolves, keeping up with the language being used to describe it has become essential to understanding its impacts .
Abliteration (a portmanteau of the words ablation, meaning to remove a part of something, and obliteration) is a process where an AI model's safety guardrails and refusal mechanisms are removed. Once an AI model is abliterated, it will not refuse requests, including harmful ones .
The patterns that a model learns during safety training to identify harmful requests can be found in a model's weights, or the billions of numerical parameters that represent its knowledge. Models that are open-weight , meaning the weights are public and can be modified, are vulnerable to abliteration.
The opening of the report, quoted unchanged from CBS News. The full text continues at the source.