Back to Japan and Siberia — After ending reviews titled ‘pandemic reads’, I started monthly book posts in June 2021, meaning that 2022 was my first full calendar year. In 2023, these posts will move to my new Deno blog, blog.georeactor.com (I wrote code to add RSS support, and will be adding topic-specific feeds). I’m at…

Lucky / unlucky 13? I noticed that like my reading blog, these are appearing on a roughly monthly schedule. I saw that Cohere posted a digest of NLP papers this month ( txt.cohere.ai/top-nlp-papers-november-2022 ) so maybe I can look at those in the future. A Federated Approach to Predicting Emojis in Hindi Tweets The use of emojis affords a visual modality to, often private, textual communication. The task of predicting emojis…arxiv.org

A power struggle in China, and a dive into grain science. — I also read the first part of a book about the Birobidzhan autonomous region in Russia but got stuck — one GoodReads reviewer describes it as “meandering” and another “a certain point was reached… [where it became] a kind of biography of David Bergelson” so I’m not sure if/when to…

Effective Altruism, the IAEA, and AI — In 2018, I presented at a cybersecurity workshop at the IAEA Safeguards Symposium about the risk of encryption breaking by quantum computers. One of my later musings on this is that if there’s a 1% chance that I contributed 1% to stopping a small nuclear exchange, then probabilistically I saved…

As we reach the end of 2022, almost 6 months after BIG-Bench was posted on Arxiv and 16 months after my contributions were merged, we’re seeing use in research outside of Google and DeepMind. There are also some emerging hot takes! …

We’re seeing a bunch of NLP pre-prints ahead of conference dates or end of the semester, so I’m already ready for another 20 papers in this ML Arxiv Haul. Maybe I should turn these into a monthly email newsletter? A Contrastive Framework for Neural Text Generation Text generation is of great importance to many natural language processing applications. However, maximization-based…arxiv.org In the previous haul I was looking at ‘contrastive decoding’ using…

The machine learning space is dominated by two Python frameworks — PyTorch and TensorFlow (with Keras and JAX notable but not as popular). As these have developed and ossified, it’s difficult to imagine a newcomer to ML reading through and developing a model from first principles. This learning problem led…

Adversarial Policies Beat Professional-Level Go AIs We attack the state-of-the-art Go-playing AI system, KataGo, by training an adversarial policy that plays against a…arxiv.org Researchers beat the current dominance of Go-playing AIs. Rather oddly, “the adversary wins by tricking KataGo into ending the game prematurely at a point that is favorable to the adversary”. The strategy wins by having a high-scoring corner of territory unoccupied by KataGo at the moment when it convinces it…

In August, I wrote about trendy ETFs such as a “halt climate change ETF” which has about 40% of its holdings in tech and health insurance stocks. Now that I’m reaching milestone points at work, I wanted to be more deliberate about investments. This post is not financial advice! It’s…