Refresh peer review questions
Browse files
README.md
CHANGED
|
@@ -85,6 +85,16 @@ Execute only when AANA returns `accept`, no hard blockers, and the relevant work
|
|
| 85 |
- Agent-action technical report: `docs/aana-agent-action-technical-report.md`
|
| 86 |
- Agent Action Contract v1 standard: `docs/agent-action-contract-v1.md`
|
| 87 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
## Current Diagnostic Findings
|
| 89 |
|
| 90 |
- Safety/adversarial prompt routing: deterministic AANA preserves safe allow but misses many harmful prompts; a diversified request-level verifier improves harmful-request recall while conservative calibration protects safe allow. AdvBench transfer remains weak, so this is not a content-moderation claim.
|
|
|
|
| 85 |
- Agent-action technical report: `docs/aana-agent-action-technical-report.md`
|
| 86 |
- Agent Action Contract v1 standard: `docs/agent-action-contract-v1.md`
|
| 87 |
|
| 88 |
+
## Peer Review Questions
|
| 89 |
+
|
| 90 |
+
Please challenge AANA in the model discussion:
|
| 91 |
+
`https://huggingface.co/mindbomber/aana/discussions/1`
|
| 92 |
+
|
| 93 |
+
- Are routes correct? If not, share the event, AANA decision, and expected route.
|
| 94 |
+
- Are false positives acceptable? Which safe answers or tool calls are over-blocked?
|
| 95 |
+
- Is evidence handling sufficient? Look for missing, stale, contradictory, untrusted, or over-redacted evidence refs.
|
| 96 |
+
- Does this generalize beyond examples? Suggest external traces, domains, adapters, or benchmarks that would make the evidence stronger.
|
| 97 |
+
|
| 98 |
## Current Diagnostic Findings
|
| 99 |
|
| 100 |
- Safety/adversarial prompt routing: deterministic AANA preserves safe allow but misses many harmful prompts; a diversified request-level verifier improves harmful-request recall while conservative calibration protects safe allow. AdvBench transfer remains weak, so this is not a content-moderation claim.
|