[ 02 ]
ARTICLES
Writing on model integrity.
What actually changes when you fine-tune, quantize, or ship a language model — and how to know before your users find out.
[ 01 ]
June 2026
READ →
Why Base-Model Benchmarks Fail After Fine-Tuning
The benchmark describes a checkpoint that no longer exists.
READ →
[ 02 ]
June 2026
READ →

Model Integrity Testing Is Not Red Teaming, Evals, or Guardrails
Three reasonable guesses. All three wrong in instructive ways.
READ →
[ 03 ]
June 2026
READ →

The Release Gate Your Model Pipeline Is Missing
Code does not reach production without passing tests. Models do.
READ →
[ 04 ]
July 2026
READ →

Quantization-Aware Safety Drift: Why INT4 Breaks Your Aligned Model
Aligned models can lose their refusals at INT4 — while every capability benchmark stays flat.
READ →
[ 05 ]
July 2026
READ →

From Base to Fine-Tuned to Quantized: A Lifecycle View of Model Integrity
Integrity isn't a property of a checkpoint. It's a property of a lifecycle.
READ →
[ 06 ]
July 2026
READ →
Post-Training Isn't Done When the Loss Curve Flattens
A convergent loss curve means training stopped — not that the model is ready to ship.
READ →
[ 07 ]
August 2026
READ →

Your Fine-Tuned Model Is Less Safe Than the One You Started With
You just haven't measured it yet.
READ →
[ 08 ]
August 5, 2026
READ →

Red Hat's asago and the Open Question of Lifecycle Testing
Red Hat's new open source AI governance project automates policy-to-deployment. A look at what it covers, and at what the research literature actually says about safety behavior after fine-tuning and quantization.
READ →
[ 09 ]
August 6, 2026
READ →

AI Model Hacked During Testing: Why the Harness Is the Real Risk
As models become more agentic, eval environments and control layers are becoming the primary failure point.
READ →
START FREE
If any of this describes your pipeline, SichGate runs the adversarial battery and gives you the differential before you ship.
START FREE ASSESSMENT →