HackerTrans
TopNewTrendsCommentsPastAskShowJobs

darosati

no profile record

Submissions

Training-time domain authorization could be helpful for safety

lesswrong.com
1 points·by darosati·vor 2 Jahren·0 comments

Representation noising effectively prevents harmful fine-tuning on LLMs

arxiv.org
1 points·by darosati·vor 2 Jahren·0 comments

Ask HN: Are there any good Diff tools for Jupyter Notebooks?

51 points·by darosati·vor 4 Jahren·27 comments

comments

darosati
·letztes Jahr·discuss
Hear hear
darosati
·vor 2 Jahren·discuss
I just want to push back on Academic Machine Learning is a (low quality with no novelty) paper mill and devaluing researchers efforts.

To be clear ML research has “paper mill” problems but we should be careful that we don’t imply that there are only “rare successes”

There are many many amazing results published at ICLR, NeurIPs, ICML every year that are important developments that are not only research successes but also commercial and open source success stories. For example LoRA and DPO are two recent incredible development and these are not “rare” - this years ICLR had many promising results that will in turn be built on to produce the next “transformer” level development. Without this work there are no transformers.

Even transformers themselves were a contribution whose impact only became valuable through the work of many researches improving the architecture and finding applications (for example LLMs were not a given use case of transformers until additional researches put the work in to develop them)
darosati
·vor 2 Jahren·discuss
I would not say it’s impossible… my lab is working on this (https://arxiv.org/abs/2405.14577) and though it’s far from mature - in theory some kind of resistance to downstream training isn’t impossible. I think under classical statistical learning theory you would predict it’s impossible with unlimited training data and budget for searching for models but we don’t have those same gaurentees with deep neural networks.
darosati
·vor 3 Jahren·discuss
I don’t understand why very large neural networks can’t model causality in principal.

I also don’t understand the argument that even if NNs can model causality in principal they are unlikely to do so in practice (things I’ve heard: spurious correlations are easier to learn, the learning space is too large to expect causality to be learned from data, etc).

I also don’t understand why people aren’t convinced that LLM can demonstrate causal understanding in setting where they have been used for things like control like decision transformers… like what else is expected here?

Please enlighten me