The public-interest problem
A changing system cannot be understood through a single frozen result.
Pre-deployment evaluation is essential, but behaviour can change through updates, tooling, permissions, routing, context and real-world interaction. The evidential record must therefore survive across time.
The observation gap
The question is not only whether a model was safe when tested.
The continuing question is what the system is doing now, what changed since the last observation and whether the evidence can be reconstructed by someone who was not present.
Systems change
Models, prompts, tools, permissions, routes, data, infrastructure and deployment contexts can all alter behaviour.
Evidence fragments
Relevant signals may be distributed across developers, evaluators, users, incident reports and external observations.
Time matters
Later knowledge can distort what was knowable earlier unless evidence is preserved in sequence.
Institutional incentives differ
Commercial, regulatory, research and public-interest actors do not hold identical information or responsibilities.
What is missing
A durable, neutral and replayable observation history.
Continuity: observations that can be compared across time rather than read as isolated snapshots.
Provenance: evidence identity, source, authority, custody and transformation that remain reconstructable.
Bounded interpretation: confidence and limitations published alongside the finding.
Independent visibility: a public-interest observation function that does not depend entirely on one actor’s incentives.
How FASO could help when built
Turn scattered signals into disciplined, reviewable observation.
The contribution is complementary. FASO would not replace developer monitoring, scientific evaluation, incident response, regulation or human judgement.
Before change
Preserve authorised baselines, identities, questions, applicable models and evidence conditions.
During change
Maintain time order, route evidence consistently and form bounded observations as new evidence arrives.
After change
Replay earlier handling, compare states, explain the supported difference and retain limitations.
For public scrutiny
Publish controlled artefacts that establish what changed and how the observation was formed without exposing unsafe detail.
The problem made concrete
Examine three real-world reference cases.
The case studies show why behavioural change, post-deployment monitoring and agentic action create a need for better observation. They are not FASO deployment claims.