Unverified50% confidenceFactExact time
Learna Tutor's input filter (checkTutorInput) contains eight categories of regex rules: privacy, crisis, bullying, medical/legal, out-of-scope, academic integrity, prompt injection, and unsafe web pages, and rejects unsupported tutor modes.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedLearna Tutor's output filter (checkTutorOutput) has a dedicated privacy check; when the tutor asks the child for personal information, that response is blocked.78% similarVerifiedAn effective prompt injection defense system typically requires a combination of input content filtering, instruction source tracing, and pre-execution intent verification, as relying solely on the model's own safety training is insufficient to resist adversarial examples.62% similarUnverifiedCore rules need to be enforced through side channels (such as hard-coded validators, independent rule-checking layers, and deterministic verification) rather than relying on conversational context.62% similarUnverifiedDeny rules directly block matching tool calls; ask rules force a confirmation prompt even in Auto Mode; allow rules broad enough to grant arbitrary code execution privileges are still sent to the classifier for re-examination.62% similarUnverifiedThe developer's rationale for choosing open-weight Gemma over closed-source hosted models is behavioral auditability, making the entire chain—including the system prompt, validators, and word count limits—auditable.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041476API
curl https://kongchang.com/api/v1/knowledge/claims/1041476MCP
get_claim(id=1041476)