What If Document Search Worked Like Navigation?
October 14, 2025

What If Document Search Worked Like Navigation?

GraphRAG uses entity extraction to build navigable graphs. What if we used embedding geometry instead? A speculative exploration of TDA for document retrieval.

8 min read→
Recovering From AI Killing Your Coding Brain
October 13, 2025

Recovering From AI Killing Your Coding Brain

How to recover from AI dependency by believing in your coding abilities and reading code instead of relying on AI assistance.

6 min read→
More Data: JEPA as a Learning Attachment for LLMs
September 18, 2025

More Data: JEPA as a Learning Attachment for LLMs

An experimental approach using JEPA Attach to test whether Joint Embedding Predictive Architectures can help Large Language Models learn from abundant multimodal data when high quality text becomes scarce.

15 min read→
Building Ambient AI For Teams
June 18, 2025

Building Ambient AI For Teams

How we instrumented Sammy 3 to feel like a teammate that sees context, speaks naturally, and acts faster than humans.

4 min read→
Shipping AI Products That Don't Suck
June 15, 2025

Shipping AI Products That Don't Suck

Lessons learned building AI features that users actually want to use—avoiding the trap of building cool tech instead of solving real problems.

10 min read→