Mini Quote Repository In ONe file
P E N T E S T I N G
The stages of a Penetration Test
[...] information-gathering
[...] threat-modeling
[...] vulnerability analysis
[...] exploitation
[...] post-exploitation
[...] reporting
Weidman, Georgia. Penetration testing: a hands-on introduction to hacking. No starch press, 2014.
T E C H N I C A L A L I G N M E N T I N A I
Making language models bigger does not inherently make them better at following a user’s intent.
For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user.
In other words, these models are not aligned with their users.
Ouyang, Long, et al. "Training language models to follow instructions with human feedback." Advances in neural information processing systems 35 (2022): 27730-27744.
We have trained language assistants that are both helpful and harmless without using human feedback labels for harmlessness.
We referred to the technique as ‘constitutional AI’ (CAI) since we used a ‘constitution’ consisting of human-written principles.
[...]
We used this method to train models that are both harmless and non-evasive, partially resolving an issue in [Bai et al., 2022].
[...]
Our ultimate goal is not to remove human supervision entirely,...
Bai, Yuntao, et al. "Constitutional ai: Harmlessness from ai feedback." arXiv preprint arXiv:2212.08073 (2022).
W I R E L E S S