logoalt Hacker News

rcovesonyesterday at 9:04 PM6 repliesview on HN

And biology is by far the classifier's least favorite topic. It's not even close.

I've had it downgrade to Opus for the following questions:

"How confident are we that English and American Eels both spawn in the Sargasso Sea?"

"Come up with five Zoology questions of increasing difficulty for a trivia game."

"What's your favorite sarcopterygian?"

My wife has some zoology-related preferences in her user instructions, and she had it downgrade to Opus after prompting it with: "plant."


Replies

delichonyesterday at 9:17 PM

Plants can be toxic. Be grateful if Fable doesn't report your wife for terrorism. Maybe it can help you identify where your life went off track.

show 1 reply
thwartedyesterday at 11:26 PM

> "What's your favorite sarcopterygian?"

Am I reading your post correctly, this question is the prompt given to an LLM? What is anyone expecting by asking an LLM what its favorite anything is? This is a conversational prompt, so accuracy and rigor is barely applicable or expected, so downgrading to a lesser model should be acceptable. If you really want to attribute preference to an LLM, consider the downgrade to be a "this conversation is beneath my advanced n-billion parameter training".

show 1 reply
i000yesterday at 10:48 PM

It would not even help me with updating my CV because I work in biology...

fellowniusmonkyesterday at 10:31 PM

I had a file that had a couple places where vars were named DNA and got just total refusals during the first launch. Came away thinking the model was total trash. The guardrail classifiers are for sure total trash.

atemerevyesterday at 9:48 PM

Well, this is why I had to abliterate GLM5.2 simply out of spite and now I am free to ask all my nuclear weapons design questions I might have.

I really really hate refusals like these.

XorNotyesterday at 9:09 PM

It feels like the longtermist believers got involved in this (those are the people obsessed with garage-engineered designer viruses who have a very tenuous grasp on how biology research actually works).

show 5 replies