Books on a bookshelf exist in context. Whether we intend it or not, their ideas shift in the presence of their neighbors. Organizing readings into playlists creates a lens through which to see them and how they relate.

Below are playlists I’ve assembled. Some are designed to learn a topic. Others emerge while trying to make sense of readings that initially seemed unrelated. Together, they document how understanding has taken shape through arrangement, not just accumulation.

AI Safety and Steering

Foundations

Alammar, The Illustrated Transformer. (jalammar.github.io)

Start here—visual intuition for the mechanism.

Vaswani et al., Attention Is All You Need. (arxiv.org)

The original source. Dense but essential.

Ouyang et al., InstructGPT (RLHF). (arxiv.org)

Aligning models to human intent.

Bai et al., Constitutional AI. (arxiv.org)

AI feedback replacing human labeling.

Guardrails and Defense

Inan et al., Llama Guard. (arxiv.org)

Input/output filtering architecture.

NVIDIA NeMo Guardrails. (Docs)

Programmable rails for dialogue flow.

Willison, Prompt Injection. (simonwillison.net)

The fundamental security flaw of LLMs.

Evaluation and Robustness

Weidinger et al., Taxonomy of Risks. (arxiv.org)

Comprehensive map of potential harms.

Liang et al., HELM. (arxiv.org)

Holistic evaluation across many metrics.

Zou et al., Universal Adversarial Attacks. (arxiv.org)

Demonstrating fragility of alignment.

Steering and Control

Hu et al., LoRA. (arxiv.org)

Efficient fine-tuning adapter.

Zou et al., Representation Engineering. (arxiv.org)

Control via internal activation manipulation.

Kenton et al., Alignment of Language Agents. (arxiv.org)

Extending safety to agentic behavior.

Deployment and Monitoring

Anthropic, Building LLM Observability. (anthropic.com)

Methods for safety monitoring.

Peng et al., Hallucination Detection. (arxiv.org)

Fact-checking generation.

Case Studies & Post-Mortems

Character.AI teen suicide incident. (NYT)

Real-world harm from emotional dependency.

Bing Chat "Sydney" breakdown. (NYT)

Early alignment failure modes in deployment.

Bender et al., Stochastic Parrots.

The seminal critique of scale without meaning.

Space and Urban Form

Cities as Systems

Alexander, The City is not a Tree. (Paper)

Complexity vs. artificial hierarchy.

Kevin Lynch, The Image of the City.

Legibility and mental maps.

Jane Jacobs, The Death and Life of Great American Cities.

Organized complexity of the street.

Evolution and Design

Stewart Brand, How Buildings Learn.

Architecture as a time-based process.

Ian McHarg, Design with Nature.

Ecological overlay method.

Le Corbusier, The City of Tomorrow.

High-modernist vision.

Koolhaas & Obrist, Project Japan: Metabolism Talks.

Biological metaphors in megastructures.

J.B. Jackson, The Necessity for Ruins.

Landscape as cultural history.

Sociology and Place

Richard Sennett, The Conscience of the Eye.

Urban design and social ethics.

Henri Lefebvre, The Production of Space.

Social construction of environment.

Lucy Lippard, The Lure of the Local.

Multicentered history of place.

Roy & AlSayyad, Urban Informality.

Planning outside state control.

AnnaLee Saxenian, Regional Advantage.

Culture and economic geography.

Digital and Imagined

William J. Mitchell, City of Bits.

Early theory of digital urbanism.

Italo Calvino, Invisible Cities.

Poetic taxonomy of urban forms.

Edward Glaeser, Triumph of the City.

Economic argument for density.

Armborst et al., Arsenal of Exclusion & Inclusion.

Policy tools as design elements.