// curated_library

Seminal papers, key talks, and essential videos from the people shaping how we think about intelligence, mind and machines — filtered for signal, not noise.

post

The Adolescence of Technology

Dario Amodei — 2026

Anthropic's CEO on the stretch he thinks we are living through: capability arriving faster than the institutions meant to hold it. He organises the danger into four kinds — systems that behave in ways nobody intended, individuals enabled to cause mass casualties, states using AI to entrench power permanently, and labour displacement outrunning the economy's ability to absorb it — and pairs each with specific mitigations rather than letting the alarm stand alone. Worth reading as much for its position as its argument: it is written by someone with a direct commercial interest in continuing to build what he is warning about, and it insists throughout that the bad outcomes are contingent rather than fated.

AI safety AI policy interpretability biosecurity concentration of power labour markets
Open ↗
post

Machines of Loving Grace

Dario Amodei — 2024

Amodei's long-form vision of how transformative AI could compress decades of scientific progress into a few years — covering biology, neuroscience, mental health, economic development and more. Essential reading on AI's potential upside.

AI futures biology AGI economic development
Open ↗
post

On the Importance of AI Safety Research

Dario Amodei — 2023

Anthropic's CEO on why safety and capability research must proceed together, not in sequence. The clearest articulation of the 'race to the top' philosophy from inside the frontier lab.

AI safety alignment Anthropic
Open ↗
paper

Claude's Model Spec (Constitutional AI)

Dario Amodei — 2024

The specification document that defines how Claude is trained to be helpful, harmless, and honest. A remarkable piece of AI alignment engineering made public.

alignment RLHF Constitutional AI safety
Open ↗