If you only realized how ridiculous your statement is, you never would have stated it.

It's also literally factually incorrect. Pretty much the entire field of mechanistic interpretability would obviously point out that models have an internal definition of what a bug is.

Here's the most approachable paper that shows a real model (Claude 3 Sonnet) clearly having an internal representation of bugs in code: https://transformer-circuits.pub/2024/scaling-monosemanticit...

Read the entire section around this quote:

> Thus, we concluded that 1M/1013764 represents a broad variety of errors in code.

(Also the section after "We find three different safety-relevant code features: an unsafe code feature 1M/570621 which activates on security vulnerabilities, a code error feature 1M/1013764 which activates on bugs and exceptions")

This feature fires on actual bugs; it's not just a model pattern matching saying "what a bug hunter may say next".

▲

mrbungie 4 hours ago | parent [-]

Was this "paper" eventually peer reviewed?

PS: I know it is interesting and I don't doubt Antrophic, but for me it is so fascinating they get such a pass in science.

	▲	ACCount37 4 hours ago \| parent [-]
		Modern ML is old school mad science. The lifeblood of the field is proof-of-concept pre-prints built on top of other proof-of-concept pre-prints.

▲

pousada 5 hours ago | parent | prev [-]

Some people are still stuck in the “stochastic parrot” phase and see everything regarding LLMs through that lense.

▲

windexh8er 4 hours ago | parent [-]

Current LLMs do not think. Just because all models anthropomorphize the repetitive actions a model is looping through does not mean they are truly thinking or reasoning.

On the flip side the idea of this being true has been a very successful indirect marketing campaign.

	▲	pousada an hour ago \| parent [-]
		What does “truly thinking or reasoning” even mean for you? I don’t think we even have a coherent definition of human intelligence, let alone of non-human ones.