meatlearner.bsky.social
Machine-learner, meat-learner, research scientist, AI Safety thinker. Model trainer, skeptical adorer of statistics.
Co-author of: Malware Data Science
11 posts
39 followers
117 following
comment in response to
post
I was surprised at how clear-cut and blatant it was. I mean, two times in a row, closed fingers, correct angle.
Meanwhile, Musk has recently issued public support for the far-right wing AfD party, often described as anti-semetic / extremist.
www.cnn.com/2024/12/20/m...
That + no apology...
comment in response to
post
Nice! Would love to be added (11 yrs in AI, co-author of Malware Data Science, love them NNs)
comment in response to
post
Am I reading this right? Techniques to make the model safe again had almost no effect on non-small models :o.
comment in response to
post
comment in response to
post
comment in response to
post
A response to X is going to be (usually) written by someone socially, politically near X's author, vs some other random piece of content Y.
It's extremely hard to take out sycophancy out of an LLM, trained the way we train them.
comment in response to
post
Say a model learns strategy x to minimize training loss --> Later, min(test loss) involves strategy y, but the model regardless sticks with strat x (inner misalignment).
Assuming outer misalignment, x can be seen as safer than y.
That being said, the better the model, the less this will happen.