I cut the AI's memory and it got smarter

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, and better at remembering the entire project. Not because I removed information, but because I str...

Olives is adding the final piece: proper visual fidelity

Olives is adding the final piece: proper visual fidelity

Almost a week ago, I built bidirectional sync between code and design tools. This weekend, I'm add...

The biggest lie in AI-assisted development

The biggest lie in AI-assisted development

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

The moat hiding in plain sight is memory

The moat hiding in plain sight is memory

Everyone's debating whether to build up or down from general AI. Nobody's talking about the moat h...

AI governance needs identity, not just rules

AI governance needs identity, not just rules

Most AI governance debates are asking the wrong question. We keep asking "how do we make AI behave ...