Research & Papers

Technical guides, research papers, and case studies

15 articles

What Building Infrastructure Taught Us About Trust

What Building Infrastructure Taught Us About Trust

Years of building infrastructure taught me that trust is earned quietly, honesty about limits beats big promises, and locking people in is a slow death.

Aug 3, 20269 min read
#infrastructure#trust#enshittification
The Hidden Energy Cost of AI, and What Low-Power Inference Could Look Like

The Hidden Energy Cost of AI, and What Low-Power Inference Could Look Like

The AI energy cost is treated as an inconsequential while the power demand is at the size of some countries and why efficiency, not scale, is the future.

Jul 18, 20267 min read
#ai energy cost#data center energy#sustainable ai

Why Data Quality Decides Small-Model Quality

On saturated consumer hardware, you do not buy small-model quality with a faster framework. You buy it with better data and a better training objective, with numbers to back it.

Jul 16, 20265 min read
#small models#data efficiency#byte-level models

LLM Decoding Without Changing Output Bytes

Speculative decoding and multi-token prediction cut byte-level generation latency without touching output quality. Here is what we measured on Veritate's models

Jul 15, 20265 min read
#speculative decoding#multi-token prediction#byte-level models

Why Low-Bit QAT Needs to Happen In Training

Below roughly four bits per weight, post-hoc QAT on byte-level models is catastrophic, and quantization-aware training recovers nearly all of the lost quality

Jul 14, 20265 min read
#quantization-aware training#post-training quantization#low-bit LLMs
Making an LLM Efficient By Optimizing Thinking Time, Not Parameter Count

Making an LLM Efficient By Optimizing Thinking Time, Not Parameter Count

For a model that must fit on a small device, the parameter budget is fixed. The place to spend is inference-time compute.

Jul 13, 20265 min read
#test-time compute#inference-time compute#small language models
Upcycling the Data Center: Doing More AI With Older Hardware

Upcycling the Data Center: Doing More AI With Older Hardware

We throw away a staggering amount of perfectly useful compute. Here is why a lot of AI and cloud work can run on older, upcycled hardware, and where it honestly cannot.

Jul 12, 20267 min read
#data center e-waste#sustainable computing#hardware lifecycle

Byte-Level Language Modeling Without a Tokenizer

Why our Veritate models read raw bytes instead of tokens, what the 256-symbol vocabulary costs, and what our 85M and 800M models tell us about the trade.

Jul 2, 20265 min read
#byte-level language model#tokenizer-free#language model research
Open Weights and the Future of Private AI

Open Weights and the Future of Private AI

Open-weight models let you run capable AI on hardware you control. Here is why I think that matters more than any leaderboard, for privacy, cost, and independence.

Jun 30, 20267 min read
#open weights#open source ai#private ai

Activation Sparsity for Efficient Inference

You cannot retrofit activation sparsity onto a finished model, but a short, cheap retrain installs it, and the savings compose with weight pruning.

Jun 12, 20265 min read
#activation sparsity#energy-efficient inference#ReLUfication
Why the Internet Forgot How to Be Efficient

Why the Internet Forgot How to Be Efficient

We ship megabytes of script to display a paragraph of text, and we call it progress. I think we forgot that efficiency was ever a virtue.

Jun 12, 20268 min read
#web bloat#efficiency#sustainable computing
The Cost of "Free" AI: Who Pays for Inference

The Cost of "Free" AI: Who Pays for Inference

Free AI is not a gift. Someone pays for every query, in energy, in data, in dependency. Here is who, and why I'd rather pay honestly for compute I control

Jun 4, 20268 min read
#cost of free ai#ai inference#ai energy use
React2Shell Explained: Carpathian's Incident Response

React2Shell Explained: Carpathian's Incident Response

CVE-2025-55182 React2Shell: Critical Zero-Day RCE. Real Cyber Attack Analysis and Threat Detection, IOCs, Remediation Steps. React & Next.js Security.

Dec 18, 202510 min read
Critical RCE in React Server Components

Critical RCE in React Server Components

React2Shell (CVE-2025-55182): Critical RCE in React Server Components. Patch to React 19.0.1+ and Next.js 15.0.5+ immediately.

Dec 16, 20259 min read
Rethinking AI Thinking

Rethinking AI Thinking

Can artificial intelligence truly think, or is it simply an extraordinarily sophisticated pattern-matching system? The people who succeed in the AI era won't be those who blindly adopt every new AI tool or those who resist all AI assistance. They'll be the ones who understand exactly what AI can and cannot do.

Nov 21, 202513 min read