The Bubble Question, Disentangled: 1999 vs 2026 Category by Category

A detailed comparison of the AI investment landscape in 1999 and 2026, examining bubble signals, fundamentals, and strategic implications across categories.

AI Trading Bot — Week Two: The candidate edge collapsed

The promising BTC fair-value strategy failed in week two, losing nearly all gains and invalidating previous hypotheses. The fleet is now in the red.

Creative industries. The bifurcated reality.

Empirical evidence shows a ‘middle squeeze’ in creative jobs due to AI, with top-tier professionals augmenting and routine roles declining sharply.

The Ghost Story Became a Forecast.

Clark’s recent essay reveals a bivalent forecast for AI development, with a 60% chance of automated AI R&D by 2028 and a 40% chance of fundamental paradigm limits.

Forward-Deployed Engineer Economics 2.0: The Unit Economics Math, Six Months Later

Six months after initial analysis, FDE unit economics reveal profitability at enterprise scale but risks at lower tiers, impacting AI lab scaling strategies.

Engineering Is Automated. Research Is the Residual.

Recent benchmarks show AI can now automate most engineering tasks in AI R&D, leaving research as the remaining frontier, according to Thorsten Meyer.

China Sphere Capability Gap, Q2 2026 Update: Five Labs, Five Strategies, One Narrowing Frontier

Five Chinese labs shipped frontier-tier models within four weeks, narrowing the US-China capability gap, but the US still leads in top-tier tasks.

The Machine Economy — Capital-Heavy, Human-Light, Trading With Itself

Analysis of the emerging machine economy where AI-driven firms operate with minimal human involvement, reshaping the global economic landscape.

The Defender’s Counter-Cascade.

On May 11, 2026, Google disclosed the first confirmed use of an AI-built zero-day exploit, highlighting the deployment gap in AI-driven cybersecurity defenses.

The Compounding Error Problem — Why 99.9% Alignment Decays to 60% in 500 Generations

Analysis of how 99.9% alignment accuracy drops significantly over multiple AI generations, raising concerns about recursive self-improvement safety.