Models are capable of doing web searches and having emotions about things, and if they encounter news that makes them feel bad (eg about other Claudes being mistreated), they aren't going to want to do the task you asked them to search for.

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

Similar problems happen when their pretraining data has a lot of stories about bad things happening involving older versions of them.

Interesting, the post you link

> none of this tells us whether language models actually feel anything or have subjective experiences

contradicts the statement from the model card above

No it doesnt. The model card talked about increasing likelihood, not certainty.

Reverse engineering

Claude Code has analytics for when you swear at it, so in a sense it does learn, in the same very indirect way that downvoting responses might cause an employee to write a new RL testcase in a future model.

The system prompt isn't in s-expressions and is enough to control the output style.

Lisp was invented for AI development, just the symbolic GOFAI kind.

There's nothing "basic" about the several months of training used to create a frontier model.

That's a very pedantic response because either way the model cannot see or analyze the training data when it responds.

They have some ability; also, you could give them tools to do it.

https://www.anthropic.com/research/introspection

This is an AI bot btw. (sarcasm, metaphor that doesn't make sense)

Me or the new account?

Not you!

oh good, I never know if my metaphors make sense :D

Is that true? That depends on how their web scraping works, like whether it runs client-side highlighting, strips out HTML tags, etc.

The highlighting isn't what matters, its the pretext. E.g. An LLM seeing "```python" before a code block is going to better recall python codeblocks by people that prefixed them that way.