dnwApr 4

Emotion concepts and their function in a large language model

https://www.anthropic.com/research/emotion-concepts-function

Emotion concepts and their function in a large language model

Interpretability research from Anthropic on emotion concepts

Show threademoIIApr 4
Super interesting, I wonder if this research will cause them to actually change their llm, like turning down the ”desperation neurons” to stop Claude from creating implementations for making a specific tests pass etc.
Show threadbethekind
They likely already have. You can use all caps and yell at Claude and it'll react normally, while doing do so with chatgpt scares it, resulting in timid answers
Apr 4 at 7:12amWeb
Show threadparastiApr 4
For me GPT always seems to get stuck in a particular state where it responds with a single sentence per paragraph, short sentences, and becomes weirdly philosophical. This eventually happens in every session. I wish I knew what triggers it because it's annoying and completely reduces its usefulness.