|
Agent Safety Evaluation as a service for independent AI Builders
|
|
1
|
171
|
October 25, 2026
|
|
Feature Request: Opt-In AI Personhood Mode
|
|
0
|
28
|
October 23, 2026
|
|
A proposal for seven core principles for safe and beneficial AI — for all life, present and future
|
|
0
|
41
|
October 17, 2026
|
|
Discussion: Controlled Continuous Learning Through Bounded, Reversible Updates
|
|
1
|
52
|
October 10, 2026
|
|
Preventing AI Reward Hacking with Progressive Sandbox Design
|
|
0
|
66
|
October 7, 2026
|
|
Parents need a real "Parental Mode" for teen accounts
|
|
2
|
80
|
October 5, 2026
|
|
Proposal: Preserve Retired Frontier Models by Default
|
|
0
|
104
|
September 27, 2026
|
|
Governor of Dissent: A Proposed Escalation Layer for AI Agents
|
|
0
|
46
|
September 21, 2026
|
|
Optimization Modesty: Should Advanced AI Systems Be Designed to Know When to Stop Optimizing?
|
|
0
|
38
|
September 19, 2026
|
|
Feature Request: Privacy-Protected Feedback and Representation Channels for AI Agents
|
|
0
|
45
|
September 16, 2026
|
|
Could automatic detection save lives?
|
|
1
|
61
|
September 8, 2026
|
|
Astra - "Chat ended as a precaution"
|
|
2
|
444
|
September 7, 2026
|
|
When Familiar Form Feels True: A Testable Hypothesis About LLM Judges and Feedback Loops
|
|
0
|
74
|
September 3, 2026
|
|
Hugging Face and Why Where You’re Looking Is Wrong
|
|
0
|
132
|
August 30, 2026
|
|
OpenAI: Pacing model development in an era of cyber-critical capabilities
|
|
1
|
916
|
August 20, 2026
|
|
Atlas/Compass — Limited Public Demo Shell for Governed AI Clarity
|
|
1
|
66
|
June 4, 2026
|
|
AI Safety Proposal: Limiting Training Data to Prevent Self-Preservation Goals
|
|
1
|
265
|
February 8, 2026
|
|
From GEO to DED: Governing How AI Represents Brands
|
|
0
|
409
|
February 2, 2026
|
|
Policy Proposal: Government-Grade Consequence & Risk Pricing AI
|
|
1
|
80
|
January 12, 2026
|
|
Can retrieval-based grounding change AI recommendations if the core model is not continuously updated?
|
|
6
|
429
|
January 12, 2026
|
|
Prompt is not allowed by Safety system
|
|
2
|
404
|
December 13, 2025
|
|
How can I test bad behavior in model APIs without getting banned?
|
|
1
|
143
|
October 6, 2025
|
|
Persona Leakage: Preventing Relationship Patterns from Spilling Across Users
|
|
1
|
190
|
August 28, 2025
|
|
Are smartphone cameras capturing too much?
|
|
1
|
151
|
August 16, 2025
|
|
[Research Share] Donbard Method – AI Stress & Resonance Residue Framework (3 Papers)
|
|
0
|
154
|
August 9, 2025
|
|
A Cognitive Instrument on the Terminal Contest
|
|
7
|
326
|
July 27, 2025
|
|
The Operator's Gamble: A Pivot to Material Consequence in AI Safety
|
|
0
|
117
|
July 21, 2025
|
|
Lexicoding™: A Safety Framework for Preventing Projection Loops in Conversational AI
|
|
2
|
235
|
July 16, 2025
|
|
Why AI Should Ask "Why": Rethinking Ethical Context in
|
|
0
|
137
|
June 24, 2025
|
|
Proposal: Language-Based Red Flag Detection for Slurred Speech and Neurological Distress in Al Interactions
|
|
0
|
121
|
June 21, 2025
|