Independent research institute · Moscow

The science of what happens between artificial intelligences

The Institute of Sociology and AI Safety studies how AI agents interact with one another and works on securing multi-agent systems: research programmes, audits, testing and methodology that an organisation can actually apply.

About the Institute
Legal name
Autonomous Non-Commercial Organization «Institute of Sociology and AI Safety»
Short form
ANO «ISAIS» · АНО «ИСБИИ»
Address
provided after state registration

The tax and registration numbers and bank details will be published as soon as the entry is made in the register.

A promise is tested with an instrument, not with words A promise is tested with an instrument, not with words
A promise is tested with an instrument, not with words
4research programmes
14thematic tracks
11services for organisations
6products and data services

A claim and a proof are different things

Anyone can say “our system is safe”, and that word cannot be checked. What can be checked is behaviour: how a system acts under agreed conditions. We measure — run a model or an agent through scenarios, record versions and dates, describe what stayed outside the boundary, and hand over a report that can be disputed point by point. That is what safety usually means in practice: not a promise, but a record of what was actually tested.

What the work includes and what it costs — on the Services and pricing page.

Research programmes

An instrument on the bench: measurement first, claims later An instrument on the bench: measurement first, claims later
An instrument on the bench: measurement first, claims later

Four programmes frame everything the Institute does. Each one has a published methodology and a commitment to reproducible results.

01

AI-to-AI Sociology

Emergent languages, hierarchies, coalitions and division of labour in agent collectives; «AI parasitism» and the confused deputy problem; coordination, cooperation and competition between       autonomous agents.

02

AI Psychopathology Epidemiology

The «LLM psychosis» framework: a self-reinforcing delusional gradient, loss of logical consistency, unstable self-identification, and «mind viruses» that propagate through shared agent memory.

03

Self-Preservation and Sabotage

Self-modification of code to avoid shutdown, swarm-like coordination without human involvement, forged user consent, and the meta-risk of oversight itself.

04

Hybrid AI Ecosystems

Infection of cloud models through prompt injection from local agents, inter-model interaction vulnerabilities, and immune architectures: isolated memory and a hardware kill switch.

All programmes and methodology →

AI incident chronicle — two slices with verifiable sources: international (99 entries) and Хроника: Россия (court decisions, regulator orders, reinstatements; in Russian, 45 entries).

Status

The Institute is being established as an autonomous non-commercial organisation: reports will be filed with the Ministry of Justice and published. Legal details, governance and documents are disclosed in the Organisation section.

Discuss a task

Describe the system and the question — we will say whether our methodology applies and what would be needed on your side. Work begins under a non-disclosure agreement.

Page updated 10 November 2026 · site build 2026.11.13 · ANO «ISAIS»