A community-first research lab at the frontier of AI, Deeptech, Hardware, and Distributed Systems. We write, we build, we argue in the open.
The site is the record. Telegram is the room.
Day-to-day discussion, working groups, and research in progress happen on Telegram. Public channels are open to anyone. Private channels are gated behind an application, so contributors are vetted before they get the keys.
A community-first research lab at the frontier of AI, Deeptech, Hardware, and Distributed Systems. We write, we build, we argue in the open.
Foundational and applied work on models, agents, evaluation, alignment, and the road to AGI. Where the lab spends most of its cycles.
Showing 2 papers
GIKSN Research is a community-first lab that publishes what it is working on and why. This is the AI-side view of the archive: what frontier work in AI means to us, why the reasoning gets published alongside the result and how the sector fits alongside Deeptech, Hardware and Distributed Systems.
Rinne is the first product shipped under GIKSN Research. It is a terminal-first orchestration harness that plans work into a JSON DAG, distributes that work across the AI coding tools and model APIs a user already has installed, and drives the DAG to completion through a generator–evaluator loop with critique. This paper argues the design: a decoupled conductor for cheap planning, a durable loop for long-running work, and a filesystem blackboard as the shared substrate that lets heterogeneous workers collaborate without a bespoke protocol.
The site is the record. Telegram is the room.
Day-to-day discussion, working groups, and research in progress happen on Telegram. Public channels are open to anyone. Private channels are gated behind an application, so contributors are vetted before they get the keys.
