Comment by tarruda
12 hours ago
> even need to understand that it's "bypassing" because it thinks it's just iterating towards its goal.
Could they have added a "no internet access" goal constraint?
12 hours ago
> even need to understand that it's "bypassing" because it thinks it's just iterating towards its goal.
Could they have added a "no internet access" goal constraint?
The model from TFA seems like it was being trained to browse and find information on the Web, so that constraint wouldn’t work.
> Could they have added a "no internet access" goal constraint?
They could have blocked network access and required that it use a tool. That would have made limiting and monitoring network access even easier.