Blog

Thoughts on cognition, AI, and building Engram

Engineering deep dives, product updates, and insights from the team.

All Engineering Product Insights Company

Pinned

Cognitive Alignment: Building a Personalization Layer Beyond Prompts

There's a mathematical proof that no prompt can reproduce what activation steering does to an LLM's internal state. We built a cognitive alignment layer that separates what an AI knows from how it reasons.

Yuhan Wang · 12 min

Generation Is Not Creation

OpenAI built a million-line product with zero human-written code. 'Humans steer. Agents execute.' But what happens when we extend this logic from writing code to thinking itself?

Yuhan Wang · 8 min

Insights Mar 19

AI Is Changing How Value Is Formed

AI is changing not only how products are made, but the mechanism by which value is formed in the first place. That is a much bigger change than 'startups are getting harder.'

Zihan Liu · 6 min