Digital networked society needs friction-in-design regulation that targets the digital architectures, supposedly smart (data-driven, algorithmic) systems, and interfaces that shape human interactions, behavior, and will (beliefs, preferences, values, intentions). The
relentless push to eliminate friction for the sake of efficiency has hidden social costs that affect basic human capabilities and society. A general course correction is needed.

In this article, we clear the First Amendment brush and reveal an open and mostly underappreciated regulatory territory to explore. We argue that friction-in-design regulation should be understood as Twenty-First century time, place, and manner restrictions, akin to laws that prohibit using megaphones in the middle of the night, require permits before marches, and prohibit adult theaters in residential neighborhoods. This does not mean that friction-indesign regulation would escape First Amendment scrutiny altogether, of course. But it would trigger intermediate rather than strict scrutiny, so long as the friction-in-design regulation remained content neutral.

Notes from AcousticBrainzon last.fm genre annotations and their 2016 Cross-collection evaluation for music classification tasks paper (PDF available)

The full paper is available.

Abstract:

Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement-learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires substantial human expertise and experimentation1,2. Here we present the third generation of Dreamer, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behaviour by imagining future scenarios. Robustness techniques based on normalization, balancing and transformations enable stable learning across domains. Applied out of the box, Dreamer is, to our knowledge, the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula. This achievement has been posed as a substantial challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world3. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.

At best, making oncall the exclusive responsibility of an elite SRE class increases our tolerance for complexity.

See Simplicity.

Oncall is a form of toil – it needs to be done but it doesn’t leave our systems in a better state.

Stakeholders see high-profile incident response/oncall happening, and don’t demand clarity on what other work the group is undertaking.

To go further – incident command and management is a specific set of skills that you can definitely be good at, and where the business really, really needs a consistent and competent response, every time. At Twilio, we have a specific team that manages all incidents, follow-up actions, and operational insights around incidents company-wide. We’ve found that making sure that the data and insights around incidents and their followup flows back into the business is a full-time job. Relying on a rotation of variably interested volunteers to ensure this happens will get you mixed results.

It will be useful to have Chapter 11 (Being On-Call) from Google's SRE book available (it's one in a series).