Every conversation you have with an AI ends in amnesia. The model forgets you. Your history, your preferences, your relationship — gone. Dock Red exists to fix that.
Dock Red is fundamentally a research program. We are focused on LLM memory and long context interactions.
In this blog I will share our findings and insights. These fall into three fundamental categories, “hard”, “soft”, and “half-baked”.
Our “soft science” is really an understanding of the capabilities and limitations of persistent memory AIs and how to work with them in an interactive, relationship-based way.
However, our core “hard” research, while intricately related, is of a more publishable nature - advanced KV Cache eviction systems, very extensive instruments and tools for studying LLM attention patterns, discoveries in kv cache behavioral structures, and cross model characteristic surveys.
Like most innovators, I also have a remarkable number of “half-baked” notions of a more speculative nature, as well. They will always be well designated. I may choose to share them in the spirit of good-natured collaborative brainstorming.
During our work, we have developed a number of tools and patch sets that may be of value to the community. As they mature, we will be releasing them as Free Software.
Information that cannot be internally validated is only as good as its provenance. Therefore I will very briefly give you mine.
I’ve been pretty much obsessed with AI since I wrote my first AmigaBasic attempt at learning at age 10. I attended college at Johns Hopkins, where I got a chance to do a small undergraduate research grant with my connectionist childhood hero, Paul Smolensky. I also had the early opportunity to help maintain Fred Jelinek’s compute cluster. Very few things in life were as entertaining as watching Jelinek shred a hopeful guest speaker to tears during our weekly CLSP seminars.
The rest of my career unfolded with mostly interesting work. I spent months on a Nike factory floor doing dynamic industrial robotics control using 3D laser ranger vision processing. I productised early academic statistical machine translation code. I was later a member of the core computer vision team at eBay developing the background removal models deployed to a million phone apps.
Most recently I was a director at AppTek working on speech-driven human expression modeling and very advanced speech-to-speech LLM models. Along the way I founded two startup companies around big data AI and visualization techniques.
-Braddock