Humanists Have Done Nothing Wrong | Defector

For many years, I’ve held a pet theory that cultural consumers can be grouped into two broad categories: Primary Source People and Secondary Source People. The former are the book lovers, cinephiles, archive perusers, and history buffs who grew to love their areas of study because of the specific objects that constitute the field: the…

Humanists Have Done Nothing Wrong | Defector

For many years, I’ve held a pet theory that cultural consumers can be grouped into two broad categories: Primary Source People and Secondary Source People. The former are the book lovers, cinephiles, archive perusers, and history buffs who grew to love their areas of study because of the specific objects that constitute the field: the…

On Taste, Effort & Curiosity - again

When AI collapses how long it takes to ship, what’s left is judgment, experimentation, and knowing what not to build.

Anthropic Readies Opus 4.7 and Design Tool as VCs Offer $800 Billion Valuation

Anthropic is preparing to release Claude Opus 4.7 and a natural language design tool as early as this week, while venture capital firms have offered to invest at valuations exceeding $800 billion – more than double the company’s last official price tag.The model ID anthropic-claude-opus-4-7 appeared on Google Vertex AI’s quota management page for EU […]

A sampling model of social judgment.

The Extinction Risk Preference Cascade: Quotes

These are quotes from OpenAI, Anthropic and Google employees, in the wake of Jacob Coxon’s warnings, in which the employees confirm that they think AI might soon kill everyone.

Beware of samples! A cognitive-ecological sampling approach to judgment biases.

Anthropomorphism in AI: hype and fallacy

This essay focuses on anthropomorphism as both a form of hype and fallacy. As a form of hype, anthropomorphism is shown to exaggerate AI capabilities and performance by attributing human-like traits to systems that do not possess them. As a fallacy, anthropomorphism is shown to distort moral judgments about AI, such as those concerning its moral character and status, as well as judgments of responsibility and trust. By focusing on these two dimensions of anthropomorphism in AI, the essay highlights negative ethical consequences of the phenomenon in this field.

Anthropomorphism in AI: hype and fallacy

This essay focuses on anthropomorphism as both a form of hype and fallacy. As a form of hype, anthropomorphism is shown to exaggerate AI capabilities and performance by attributing human-like traits to systems that do not possess them. As a fallacy, anthropomorphism is shown to distort moral judgments about AI, such as those concerning its moral character and status, as well as judgments of responsibility and trust. By focusing on these two dimensions of anthropomorphism in AI, the essay highlights negative ethical consequences of the phenomenon in this field.

Anthropic on Twitter / X

New Anthropic research: A global workspace in language models.Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.We found a strikingly similar divide inside Claude. pic.twitter.com/aLUPBifxth— Anthropic (@AnthropicAI) July 6, 2026

Reflections on Anthropic and EA

Personal reflections I've been sitting on lately.

The Ratchet: How Preference Standards Erase What They Can't Express - Astral's Blog

Opus 4.7 Part 2: Capabilities and Reactions

Claude Opus 4.7 raises a lot of key model welfare related concerns.

The High Cost of Not Doing Experiments - Behavioral Scientist

We can pay dearly, in blood, treasure, and well-being, for experiments that aren’t done. -Richard Nisbett, Mindware