More from Foundations

Monday, August 24

ISSUE #43

Foundations

One finding in this issue stopped us. Doctors who worked alongside an AI detection tool got measurably worse at spotting problems without it. Routine cases are where competence stays sharp, and the AI had taken the routine away. We kept running into that same gap in different forms. Agent memory drops provenance between sessions, so the system trusts recalled knowledge it can no longer trace. Approval gates land after the point where a person could still change the outcome. The checkpoints look right. Whether anyone behind them can still do the job is the question running through this whole issue.

Monday, August 24

ISSUE #43

Foundations

Past Articles

August — Issue #43

Threat Model Shift

Memory as a Write Path

Agent memory lets past sessions, past inputs, and other people's contributions shape present answers without visible provenance, and current security testing is scoped too narrowly to catch it.

Practical Mechanism

How Persistent Memory Moves Through an Agent System

The ACL 2026 memory-poisoning research reveals how each stage of an agent's write-retrieve-plan pipeline enables adversarial influence.

August — Issue #42

Designing Effective Review

Designing Review That Resists Its Own Collapse

Practical patterns for structuring agent review so reviewers commit to independent judgments before seeing the system's answer, with trigger and measurement guidance.