Portfolio Approach to AI Safety Research

[This article originally appeared on the Deep Safety blog.]

dimensionsLong-term AI safety is an inherently speculative research area, aiming to ensure safety of advanced future systems despite uncertainty about their design or algorithms or objectives. It thus seems particularly important to have different research teams tackle the problems from different perspectives and under different assumptions. While some fraction of the research might not end up being useful, a portfolio approach makes it more likely that at least some of us will be right.

In this post, I look at some dimensions along which assumptions differ, and identify some underexplored reasonable assumptions that might be relevant for prioritizing safety research. In the interest of making this breakdown as comprehensive and useful as possible, please let me know if I got something wrong or missed anything important.

Continue reading “Portfolio Approach to AI Safety Research”

Death Note: Finally, an Anime about Deep Learning

It’s about time someone developed an anime series about deep learning. In the last several years, I’ve paid close attention to deep learning. And while I’m far from an expert on anime, I’ve watched a nonzero number of anime cartoons. And yet through neither route did I encounter even one single anime about deep learning.

There were some close calls. Ghost in the Shell gives a vague pretense of addressing AI. But the character might as well be a body-jumping alien. Nothing in this story speaks to the reality of machine learning research.

In Knights of Sidonia, if you can muster the superhuman endurance required to follow the series past its only interesting season, you’ll eventually find out that the flying space-ship made out of remnants of Earth on which Tanikaze and friends photosynthesize, while taking breaks from fighting space monsters, while wearing space-faring versions of mecha suits … [breath] contains an artificially intelligent brain-emulating parasitic nematode. But no serious consideration of ML appears.

If you were looking to anime for a critical discourse on artificial intelligence, until recently you’d be disappointed.

Continue reading “Death Note: Finally, an Anime about Deep Learning”

Do I really have to cite an arXiv paper?

With peak submission season for machine learning conferences just behind us, many in our community have peer-review on the mind. One especially hot topic is the arXiv preprint service. Computer scientists often post papers to arXiv in advance of formal publication to share their ideas and hasten their impact.

Despite the arXiv’s popularity, many authors are peeved, pricked, piqued, and provoked by requests from reviewers that they cite papers which are only published on the arXiv preprint.

“Do I really have to cite arXiv papers?”, they whine.

“Come on, they’re not even published!,” they exclaim.

The conversation is especially testy owing to the increased use (read misuse) of the arXiv by naifs. The preprint, like the conferences proper is awash in low-quality papers submitted by band-wagoners. Now that the tooling for deep learning has become so strong, it’s especially easy to clone a repo, run it on a new dataset, molest a few hyper-parameters, and start writing up a draft.

Of particular worry is the practice of flag-planting. That’s when researchers anticipate that an area will get hot. To avoid getting scooped / to be the first scoopers, authors might hastily throw an unfinished work on the arXiv to stake their territory: we were the first to work on X. All that follow must cite us. In a sublimely cantankerous rant on Medium, NLP/ML researcher Yoav Goldberg blasted the rising use of the (mal)practice. Continue reading “Do I really have to cite an arXiv paper?”