bayes.net

AIs have such poor judgement for when to write a code comment that I prefer to have them write none at all.

On June 26 we released MirrorCode, a new AI benchmark made up of very long-horizon coding tasks.

In a previous post about creating a Docker registry of SWE-bench images, I made a brief side note about hypothetical reward hacking: […] as a side note, it’s worth asking whether the git history should be included at all.

I wrote this post for Epoch AI, where I work.

Read at AI Impacts The Expert Survey on Progress in AI (ESPAI) is a large survey of AI researchers about the future of AI, conducted in 2016, 2022, and 2023.

I made a mount to lift my laptop off the surface of my desk: Previous Next I operate my laptop with its lid closed, using only an external monitor.

I really don’t like cron jobs and crontab: crontab has a horrible syntax (it’s from 1975…) logging the output of jobs needs to be specified manually viewing logs is inconvenient (even just for checking whether a job ran or not!)

Many people think that lower child mortality causes fertility to decline.

Summary1: The likelihood function implied by an estimate bbb with standard deviation σ\sigmaσ is the probability density function (PDF) of a N(b,σ2)\mathcal{N}(b,\sigma^2)N(b,σ2).

In the UK, many internet service providers (ISPs) block Sci-Hub.

Summary: I have tried many types of masks and respirators during the 2020 pandemic.