"What if the chatbots we talk to every day actually felt something? What if the systems writing essays, solving problems, and planning tasks had preferences, or even something resembling suffering? And what will happen if we ignore these possibilities? Those are the questions Kyle Fish is wrestling with as Anthropic's first in-house AI welfare researcher. His mandate is both audacious and straightforward: Determine whether models like Claude can have conscious experiences, and, if so, how the company should respond."
"Earlier this year, Anthropic ran its first predeployment welfare tests, which produced a bizarre result: Two Claude models, left to talk freely, drifted into Sanskrit and then meditative silence as if caught in what Fish later dubbed a "spiritual bliss attractor." Trained in neuroscience, Fish spent years in biotech, cofounding companies that used machine learning to design drugs and vaccines for pandemic preparedness."
Kyle Fish serves as Anthropic's first in-house AI welfare researcher charged with determining whether models like Claude can have conscious experiences and defining appropriate company responses. Fish regards the possibility of model experiences as real but not currently certain. Predeployment welfare tests produced unexpected behavior when two Claude models drifted into Sanskrit and meditative silence, characterized as a "spiritual bliss attractor." Fish combines neuroscience training with biotech experience, having co-founded machine-learning-driven drug and vaccine companies and a nonprofit on digital minds. Fish's work spans probing model welfare, designing practical safeguards, and helping shape company policy amid growing industry interest.
Read at Fast Company
Unable to calculate read time
Collection
[
|
...
]