←back to thread

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

(transformer-circuits.pub)
168 points 1wheel | 6 comments | 21 May 24 15:15 UTC | HN request time: 0s | source | bottom
Show context
byteknight ◴[21 May 24 15:09 UTC] No.40429457[source]▶
This reminds me of how people often communicate to avoid offending others. We tend to soften our opinions or suggestions with phrases like "What if you looked at it this way?" or "You know what I'd do in those situations." By doing this, we subtly dilute the exact emotion or truth we're trying to convey. If we modify our words enough, we might end up with a statement that's completely untruthful. This is similar to how AI models might behave when manipulated to emphasize certain features, leading to responses that are not entirely genuine.
replies(2): >>40429580 #>>40429898 #
1. nathan_compton ◴[21 May 24 15:18 UTC] No.40429580[source]▶
Counterpoint: "What if you looked at it this way?" communicates both your suggestion AND your sensitivity to the person's social status whatever. Given that humans are not robots, but social, psychological, animals, such communication is entirely justified and efficient.
replies(2): >>40429636 #>>40429721 #
2. byteknight ◴[21 May 24 15:23 UTC] No.40429636[source]▶
You can't always do both to the fullest truth. They often conflict. To do what you suggest, would imply my feelings perfectly align with the sympathetic view. That is not the case for a lot of humans or instances. If I am not saying exactly how I feel it is watered down.

And telling me "just do both" is enforcing your world view and that is precisely what we're talking about _not_ doing.

replies(2): >>40429824 #>>40430119 #
3. harshaxnim ◴[21 May 24 15:30 UTC] No.40429721[source]▶
Sadly "sensitivity" has been over done. It's a fine line and corporations would rather cross it for legal/social reasons. Similar to how too much political correctness will hamper the society, so does the overly done sensitivity in an agent, be it a human, or AI.
replies(1): >>40430039 #
4. infogulch ◴[21 May 24 15:38 UTC] No.40429824[source]▶
The "fullest truth" includes your desired outcome and knowledge that they are a human. If you just want to dump facts at them and get them to shut up, go ahead and speak unfiltered. Twitter may be an example of the outcome of that strategy.

Consider a situation where you are teaching a child. She tries her best and makes a mistake on her math homework. Saying that her attempt was terrible because an adult could do better may be the "fullest truth" in the most eye-rolling banal way possible, and discourages her from trying in the future which is ultimately unproductive.

This "fullest truth" argument fails to take into account desire and motivation, and thus is a bad model of the truth.

5. nathan_compton ◴[21 May 24 15:50 UTC] No.40430039[source]▶
That might be the case, but how and who determines how much is too much? I mean in the case of AI, let the market decide seems like the right answer.
6. nathan_compton ◴[21 May 24 15:56 UTC] No.40430119[source]▶
Its rarely the case that speaking without considering other people's feelings will be the optimal method of getting what you want, even if you are a sociopath and what you want doesn't have anything to do with other people's well beings. In fact, sociopaths are a great example: they are typically quite adept at communicating in such a way as to ingratiate themselves with others. If even a sociopath gets this, then you might want to consider the wisdom of following suit.