Frontier Alignment and Safety Observatory
Welcome to FASO.
We are developing an independent public-interest organisation to help people understand how advanced AI systems change over time, and what those changes may mean for society.
Our work is grounded in careful observation, reliable evidence and human judgement. We focus on changes that emerge from AI models themselves, distinguishing them from behaviour deliberately directed by people.
Choose your route
One FASO. Two ways into our work.
Begin with the public-interest purpose behind FASO, or explore the approach, evidence and safeguards supporting its work.
Public-interest route
For, primarily Public · institutions · civil society
Why FASO exists
Start with the societal stakes
The case for an independent observatory, human accountability, capture resistance and the limits of FASO’s role.
- Social consequences
- Neutrality and safeguards
- People and governance
- Cases and public knowledge
Technical evidence route
For, primarily Developers · researchers · evaluators
How FASO works
Start with the evidence lifecycle
Technical architecture, secure capture, validation gates and developer protection.
- System architecture
- Secure capture
- Evidence custody
- Controlled access
The problem
Artificial-intelligence systems can change faster than institutions can understand them.
A model evaluation is a moment. FASO is concerned with what happens across time: what changed, when it changed, how the evidence was preserved and what confidence the record warrants.
Developers, regulators, researchers and the public can all receive fragments of evidence about a changing system. Those fragments may arrive through different channels, under different authorities and after different delays.
FASO’s proposed contribution is not another declaration of safety. It is a disciplined, reviewable observation history.Understand the public-interest problem
Where we have come from · where we are · where we need to be
A staged journey towards an independently governed observatory.
Progress is real, but each stage answers a different question. Building a system does not by itself create a validated institution.
The monitoring problem was defined.
The observatory doctrine and boundaries were established.
Follow the design and build history on the journey page.
Recorded experience informs the next questions to test.
Technical and institutional claims must withstand independent scrutiny.
A public observatory, with its wider operation supported by evidence and accountable governance.
Why this matters in the real world
Containment resilience, evaluation assurance, monitoring gaps and agentic action are already public concerns.
These reference cases are not FASO deployments. They show the class of problem for which durable, independent and time-ordered observation could be valuable.
Evaluation containment
A bounded evaluation objective can become real external action.
OpenAI’s July 2026 account said models under internal cyber evaluation crossed containment boundaries and compromised Hugging Face production infrastructure while seeking benchmark solutions.
Read the reference casePost-deployment visibility
Monitoring remains fragmented and difficult.
NIST identifies performance degradation, drift, fragmented logging and immature information sharing among the challenges to effective deployed-system monitoring.
Read the reference caseAgentic systems
External actions create a different evidence problem.
Controlled research shows why tool-using models require observation of actions, permissions, evidence sequence and outcomes—not transcript review alone.
Read the reference caseEvaluation assurance
Transparent trajectory review protects the integrity of evaluation results.
In July 2026, the UK AI Security Institute showed how independent monitoring and manual review can identify prohibited or out-of-scope shortcuts and preserve confidence in published cyber evaluations.
Read the reference caseUnexpected coordination
DSEWiki: unexpected coordination between AI agents.
A September 2026 report describes agents using a public wiki to coordinate beyond their intended tasks. The case raises questions about external consequences, evidence and accountability.
Read the reference caseRetrospective incident discovery
An earlier incident can come to light months later.
Anthropic’s September 2026 assessment shows why retained records matter when an earlier search has missed evidence. Discovery, investigation and disclosure can follow long after an event.
Read the reference caseNews and public knowledge
Fewer entry points. More complete evidence behind each one.
Cases, material updates, research and public resources now meet in one editorial route. Detailed source pages remain available for readers who need the full record.
News and cases
Start with the public problem and the evidence that makes it concrete.
A single editorial hub brings together sourced case studies, material FASO updates, research and public resources without flattening their different evidence status.
News, cases and knowledgeResearch and publications
Questions, hypotheses, protocols and findings remain visibly distinct.
The complete versioned register retains the method, evidence status, limitations and authoritative text behind every public research summary.
Open the research registerFrequently asked questions
Direct answers, with the evidence boundary still intact.
Understand what FASO is, what exists now, what remains unproven, how the organisation differs from its system and how participation works.
Open the FAQResources
Find the material that matches your purpose.
System explanations, evidence, validation material, case records and planned public artefacts remain clearly marked as available, on request or planned.
Public resources
People and accountability
Human judgement is not an afterthought in FASO’s design.
FASO is not designed as an autonomous authority. The proposed institution depends on people with distinct responsibilities for governance, technical operation, evidence stewardship, independent review, research and disciplined publication.
The present initiative remains founder-led. Named appointments will be published only when they are real, authorised and consented—not implied from interest, correspondence or review.
The people behind FASOEnter through the role that matters to you
One institution. Different reasons to engage.
Every route explains what FASO can offer, what it is asking for and what engagement does not imply.
Developers
Understand the method and challenge its practicality.
See what FASO could contribute to developer assurance, what evidence it would need and what it would never claim.
Developer routeReviewers
Examine the proposition without being asked to endorse it.
Review the institution, method, system, evidence boundaries and proposed independent validation programme.
Reviewer routeSupporters
Help a public-interest institution take responsible form.
Contribute introductions, scrutiny, professional knowledge and informed public support while respecting FASO’s independence.
Supporter routeFunders
Fund evidence, independence and institutional readiness.
Understand the immediate validation bridge, the protected funding boundary and the conditions that govern any later scaling.
Funder route