Showing Posts From

Token-efficiency

• Moe Hachem
• February 18, 2026
• • AI architecture,
  • Research

SR-SI context savings scale progressively

AI context savings that work like taxes should: progressive. Small repos see 10-20% efficiency gains...

• Moe Hachem
• February 20, 2026
• • AI architecture,
  • Product strategy

The biggest lie in AI-assisted development

The biggest lie in AI-assisted development: "Just generate better specs and your problems will go aw...

• Moe Hachem
• February 21, 2026
• • AI architecture,
  • Research

I cut the AI's memory and it got smarter

I gave an AI a 15,800 token memory. Then I cut it to 3,300 (update: make it 1.6k). It got smarter,...

• Moe Hachem
• February 22, 2026
• • AI architecture,
  • Research

SR-SI: The methodology that gives AI persistent memory across any long-running project

106x performance improvement. A self-improving loop. And a section nobody expected to write. V2 is ...

• Moe Hachem
• February 25, 2026
• • Builder,
  • AI architecture,
  • Product strategy

How I maintain coherence across 66,000 lines of code without losing the thread

Most AI-augmented development workflows break somewhere between promt 50 and 200, or as I've come to...

• Moe Hachem
• February 27, 2026
• • AI architecture,
  • Research

Computation is killing collaboration

Computation is killing collaboration. The biggest hurdle in AI-assisted development isn't a lack of...

• Moe Hachem
• February 28, 2026
• • AI architecture,
  • Research,
  • Professional Practice

Why I went the opposite direction from spec-first

Everyone's rushing to AI tools that promise "comprehensive specs in one prompt." I went the opposit...

• Moe Hachem
• March 30, 2026
• • Ai architecture,
  • Research,
  • Systems

Why AI context degrades — and the architectural fix that actually works

Every team that works with AI long enough hits the same wall. The sessions start sharp. The model kn...