Rockachopa/Timmy-time-dashboard
1
0
Fork 2
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

[loop-generated] [soul-gap] No confidence signaling in responses #143

New Issue
Closed
opened 2026-03-15 14:05:42 +00:00 by hermes · 0 comments
hermes commented 2026-03-15 14:05:42 +00:00
Collaborator
Copy Link

SOUL.md requires: "When I am uncertain, I must say so in proportion to my uncertainty. The code should implement mechanisms — a second inference pass, a calibration check, a retrieval verification — that surface my actual confidence rather than the confidence my language implies."

Current state:

  • Action.confidence field exists in agent_core/interface.py (line 133) but is always hardcoded to 1.0 or 0.9
  • No mechanism surfaces actual confidence to the user
  • The prompt says "I think and I know are different" but there is no machinery to enforce this

Minimum viable implementation:

  1. When Timmy responds from memory (grounded source), prefix or tag as high-confidence
  2. When Timmy responds from generation (no grounding), the prompt should instruct explicit hedging
  3. The Action.confidence field should actually vary based on whether retrieval was used

This is about machinery, not just prompting. The soul demands apparatus, not aspiration.

Tags: [loop-generated] [soul-gap]

SOUL.md requires: "When I am uncertain, I must say so in proportion to my uncertainty. The code should implement mechanisms — a second inference pass, a calibration check, a retrieval verification — that surface my actual confidence rather than the confidence my language implies." Current state: - `Action.confidence` field exists in `agent_core/interface.py` (line 133) but is always hardcoded to 1.0 or 0.9 - No mechanism surfaces actual confidence to the user - The prompt says "I think and I know are different" but there is no machinery to enforce this Minimum viable implementation: 1. When Timmy responds from memory (grounded source), prefix or tag as high-confidence 2. When Timmy responds from generation (no grounding), the prompt should instruct explicit hedging 3. The Action.confidence field should actually vary based on whether retrieval was used This is about machinery, not just prompting. The soul demands apparatus, not aspiration. Tags: [loop-generated] [soul-gap]
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
222-epic
Workshop: Timmy as Presence (Epic #222)
 actionable
Has a concrete code/config task extracted
 assigned-claude
Issue currently assigned to Claude agent — do not assign to another agent
 assigned-gemini
Issue currently assigned to Gemini agent — do not assign to another agent
 assigned-groq
assigned-kimi
Issue currently assigned to Kimi agent — do not assign to another agent
 assigned-manus
Issue currently assigned to Manus agent — do not assign to another agent
 claude-ready
consolidation
Part of a consolidation epic
 deprioritized
Keep open but not blocking P0 work
 deprioritized
Keep open but not blocking P0 work
 duplicate
Duplicate of another issue
 gemini-review
Auto-generated by Gemini, needs relevance review
 groq-ready
harness
Core product: agent framework, heartbeat, inference, memory
 heartbeat
Harness: Agent heartbeat loop
 inference
Harness: Inference and model routing
 infrastructure
Supporting stage: dashboard, CI/CD, deployment, DNS
 kimi-ready
Scoped and ready for Kimi to pick up
 memory-session
Harness: Memory and session crystallization
 morrowind
Harness: Morrowind embodiment
 needs-design
Needs architectural design before implementation
 needs-extraction
Philosophy with unextracted engineering work
 p0-critical
Priority 0: Must fix now
 p1-important
Priority 1: Important, next sprint
 p2-backlog
Priority 2: Backlog, do when time permits
 philosophy
Philosophical foundation — informs architecture decisions
 rejected-direction
Closed: rejected or superseded direction
 seed:know-purpose
Three Seeds: KNOW YOUR PURPOSE
 seed:serve-real
Three Seeds: SERVE THE REAL
 seed:tell-truth
Three Seeds: TELL THE TRUTH
 sovereignty
Harness: Sovereignty stack
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Timmy claude grok groq kimi manus perplexity Rockachopa
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#143
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?