Observation · evidence · human judgement
How FASO works
FASO helps people examine how AI behaviour changes over time. Our focus is on changes that emerge from the model itself, rather than behaviour deliberately directed by people. We bring together observation, a dependable record and human judgement to understand what the evidence can tell us.
Current technical status · updated 9 October 2026
Operating observations, bounded demonstrations and independent validation ahead.
The development record now includes completed agent-observation work and recorded permission tests. Independent assessment is still needed to establish reliability and readiness for wider use.
Technical foundation
An observation system and end-to-end testing environment are in place. Internal checks support development and review; they are distinct from independent validation.
Regular interval observation
The programme covers Qwen3-8B, IBM Granite Vision 3.2-2B, Claude Sonnet 5 and OpenAI Sol 5.6. The September record describes observed answer changes and the notification evidence, with the cause unresolved. This editorial update is not a fresh check of every scheduled run.
Agent activity and delegation
DAM and DAMFFD followed a working agent and one level of delegation in the 4–5 October demonstrations. The final report-export component finished inactive. These results do not establish unrestricted monitoring.
Permission evidence and review workflow
A recipient-permission checker and operator review workflow were demonstrated using retained evidence. The 9 October results preserve evidence gaps and earlier decisions. Reliability on unseen agents and live prevention remain unestablished.
Continuous monitoring
The completed demonstrations do not establish continuous observation across the AI model ecosphere. Wider integration, coverage and assurance remain development work.
Independent validation
Independent external validation has not been completed. Additional funding is being sought for detailed validation of the system and the organisational design.
The work in practice
From observation to a finding people can examine.
01 · Context
Establish what is being observed
We record which model is being observed, its stated version and the conditions of the observation. This context helps reviewers consider known developer updates or changes in how the model is being used.
02 · Observation
Follow behaviour over time
FASO retains observations with their source and timing, so later behaviour can be examined alongside earlier behaviour. The original evidence remains available for authorised review.
03 · Review
Examine a possible change
When a difference is identified, people examine the evidence and consider alternative explanations, including deliberate changes by a developer or user. A difference alone does not establish model-derived drift, its cause, harm or intent.
04 · Communication
Explain what the evidence supports
Findings explain what was observed, when it happened and what remains uncertain. Where appropriate, the relevant developer is notified. Wider sharing follows the permissions and confidentiality arrangements for the evidence.
Evidence that can be examined.
A useful record shows both what happened and how the understanding of it developed. The time of an observation, the time a change was recognised and any later review are kept distinct, so earlier evidence can be revisited without losing what was known at the time.
Read the evidence review guideExplore the evidence and safeguards
Follow the detail that matters to you.
How FASO handles evidence
Understand the organisation’s responsibilities for access, protection, review and publication.
Read the organisational safeguardsTesting and independent validation
See how internal testing differs from an independent assessment of validity.
Understand validationDeveloper participation
Explore the purpose, protections and expectations of participation.
Developer informationThe organisation behind the work
See the public-interest purpose FASO is being built to serve.
Explore the six organisational priorities, the proposed safeguards and the work still needed to establish the institution.