Department
Field Reports
Field Reports are practitioner walk-throughs. A contributor with direct access to a working audit, a deployment scenario, or a production system writes about what they saw and what they could and could not verify. Field Reports are the publication's closest thing to a how-to column — without ever quite landing on a single right answer.
7 pieces · Department RSS
Recommended
Full archive — Field Reports
- 2026-06-11
The Activation-Patching Renaissance — What Circuits Research Found in 2025
Activation patching, a technique that traces causal contribution of specific model components to specific outputs, moved from a niche mechanistic-interpretability technique to one of the field's mo…
- 2026-06-08
AI Red-Teaming Methods Compared — Anthropic, OpenAI, DeepMind
Three frontier labs publish red-teaming methodology. The methods diverge enough that a reader who reads them carefully can form a working view of what each lab thinks pre-deployment safety evaluati…
- 2026-05-19
DeepMind's Frontier Safety Framework — How 'Critical Capability Levels' Work
Google DeepMind's Frontier Safety Framework defines a tiered evaluation regime for frontier model capabilities and binds the lab's deployment posture to thresholds it has committed to in public. A …
- 2026-02-17
The Compliance Edge: Why AI Marketing Stacks Need Audit Layers
AI marketing was, until recently, an unregulated category. The shift to agentic marketing pipelines — automated outreach, automated segmentation, automated content — is putting it inside regulatory…
- 2025-12-02
Inside an Agentic Audit: A Hypothetical Walkthrough
A composite scenario, drawn from the patterns of real audit engagements. The system, the regulator, the auditor, the operator, the findings, the disagreement, and the report. Notes on what goes wro…
- 2025-11-18
The Interpretability Stack: A Practitioner's Toolkit
What an interpretability practice actually consists of in 2026, layer by layer. A working toolkit, with notes on which layers are mature, which are research-grade, and which are still mostly market…
- 2025-11-05
Ten Operators Building Auditable AI Systems
A reluctant listicle. We do not normally publish them. We are publishing this one because the gap between 'firms that claim auditability' and 'firms that ship it' has gotten wide enough to warrant …
Bylines active in this department
Browse every department and tag, or read the full archive in chronological order.