A python library built on top of UKAISI Inspect to support Control research, by Redwood

Research developing AI control protocols using task decomposition

🚦🗺️ UrbanFlow AI is a web app for generating 3D traffic simulations from real OpenStreetMap areas. It builds SUMO scenarios, runs microscopic vehicles, pedestrians, buses and trams, edits road events, controls real traffic lights with TraCI, trains JSON AI policies, saves models, and shows live metrics, charts, and notebooks.

An intelligent traffic management system that dynamically adjusts highway lane configurations using AI-powered congestion detection and a movable median barrier.

Judge-first framework where LLM outputs must converge under explicit, adversarial oracles.

Python client for Aegis — stabilize AI systems instantly with a simple API call.

In-depth exploration of Large Language Models (LLMs), their potential biases, limitations, and the challenges in controlling their outputs. It also includes a Flask application that uses an LLM to perform research on a company and generate a report on its potential for partnership opportunities.

Kho lưu trữ này chứa tài liệu, bài tập, và mã nguồn liên quan đến môn Trí tuệ nhân tạo trong điều khiển. Môn học tập trung vào ứng dụng AI trong các hệ thống điều khiển tự động, bao gồm lý thuyết và thực hành.

AI Governance — human-controlled code injection with oversight

Independent AI governance and control standard

Lichtarbeit

GG Tank Watch - frozen public-information archive of a resolved May 2026 chemical emergency. Conduit-only design; responsible-AI safety patterns enforced in code and tests.

AutoRed: Measuring the Elicitation Gap via Automated Red-Blue Optimization — AI Control Hackathon 2026

The project evaluates whether a lightweight hardening layer can recover robustness without redesigning the surrounding protocol. The method combines transcript sanitization, explicit instruction-data separation, and an optional prompt-diversity ensemble.

Control protocols robust to a monitor-aware adversary — empirical AI-control eval on the APPS backdoor testbed (open-weight models).

Train and optimize AI model behavior with configurable limit constraints.

AI-control research prototype testing fingerprint-aware untrusted LLM policies (within sandboxed model weight-exfiltration tasks) against matched LinuxArena model-registry honeypots under Control Tower's trusted-monitoring blue protocols and matched-decoy telemetry

Non-throne AI governance canon for anti-capture, provenance grounding, advisory-only alignment, challenger comparison, and external origin-coordinate evaluation.

The website for the paper "Control Tax: The Price of Keeping AI in Check." The paper: https://arxiv.org/abs/2506.05296

A practical safety and recovery design package for AI / LLM-based control systems. Defines where AI can be used, where it must be stopped, and how systems recover.