Topic starter
25/10/2026 11:09 am
TL;DR: Fable 5 can reroute risky requests to a weaker model, refuse opaque prompts, and change behaviour by conversation position, according to Tego AI. Fable 5’s routing layer now makes placement part of the control path, so governance has to account for fallback strength as well as refusal.
Editorial analysis by NHI Mgmt Group, based on content published by Tego AI: “Same Words, Different Doors: Notes on Fable 5’s Safety Mechanism and Its Position-Sensitive Routing”.
Key questions
Q: Why does fallback routing create governance risk for AI systems?
A: Fallback routing changes the capability profile of the answer without ending the interaction, so the control is no longer just allow or deny.
Q: What breaks when AI safety decisions depend on conversational position?
A: A single static prompt policy no longer guarantees a single outcome.
Q: How should teams validate position-sensitive AI safety routing?
A: Test the same content in multiple locations within the conversation, including the newest user turn, earlier assistant output, system instructions, and tool results.
Practitioner guidance
- Test routing against conversation position Run the same prompt as the latest user message, prior assistant output, system content, and tool output, then compare the routing result.
- Separate fallback and refusal telemetry Record fallback, refusal, and normal-answer states as distinct outcomes in logs, audit trails, and alerting so downstream systems do not collapse them into one event type.
- Review tool-output surfaces as governed input Treat MCP or other tool results as evaluated content, not just metadata, because the classifier may react to text that arrives through tool channels.
Bottom line: Fable 5’s router shows that AI safety controls can be position-sensitive, not just content-sensitive.
Glossary terms: Position-Sensitive Routing, Fallback Model, Streaming Refusal, Tool Output Surface
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
This topic was modified 7 days ago by NHI Mgmt Group
27/10/2026 7:14 pm
Position-sensitive routing is an identity governance problem, not just a model-safety feature. The article shows that the same text can be treated differently depending on where it sits in the conversation. That means the real control boundary is the request surface, not the prompt string alone. For practitioners, the implication is that governance has to model conversational context as part of authorisation and review.
A question worth separating out:
Q: How should security teams handle tool outputs in AI routing controls?
A: Treat tool outputs as first-class input to the safety layer, because they can influence routing just like a user message. That means tool content needs the same scrutiny as prompt content, especially when it can inject security-sensitive language or transformed text. Governance fails if tool output is assumed to be harmless context rather than evaluated content.
👉 Read our full editorial: Fable 5’s routing gate shows how safety classifiers split sessions
This post was modified 7 days ago by NHI Mgmt Group