About — R&D Amplifier

An instrument for attention.

A personal research-intelligence platform: one fully local brain that reads scientific papers end-to-end, builds a knowledge graph, and rewrites what matters into practical articles.

Reading everything is impossible. Missing the twelve papers that matter is unacceptable. The answer is not another feed fighting for your attention — it is an *instrument* that reads on your behalf and shows its work.
01 / 03

All inference is local

The whole pipeline runs on one host. No paper, draft or prompt ever leaves the machine — your research interests stay yours. Self-speculative decoding gives 2.1× throughput on a single GPU, with no second model to host.

vLLM · NVFP4 · NVIDIA DGX Spark
02 / 03

Provenance on the page

Articles are openly AI-generated, and the trail sits next to the text, not in a footnote: the authoring model, the persona it wrote as, and the evaluation score it cleared. Honest, with no asterisks.

model · persona · eval score
03 / 03

Gates, not feeds

Nothing reaches you because an algorithm thinks you will engage. Two quality gates decide: a signal score on the paper itself, and an evaluation score on the draft. Below threshold — regenerate or discard.

signal gate · eval gate
0
forge stages
0
quality gates
0
articles published
0%
local inference
Personas

One brain, many voices.

habr_engineer

The Engineer

Benchmarks, trade-offs, deployment notes. Writes like a senior colleague reviewing a paper for the team channel.

engineering_deepdive
science_essayist

The Essayist

Finds the story inside the method. For results that change how you see the field, not just how you use it.

narrative_discovery
lesswrong_skeptic

The Skeptic

Stress-tests the claims: confounds, baselines, what the authors did not run. Healthy doubt, in writing.

critical_review
academic_accessible

The Lecturer

Patient, precise explanations that survive contact with a non-specialist — without dumbing the result down.

explainer