|
Preventing Incentive Leakage in ChatGPT App Integrations
|
|
1
|
86
|
January 10, 2026
|
|
How can two stage gates improve non generative analytic workflows?
|
|
6
|
67
|
December 15, 2025
|
|
Prompt is not allowed by Safety system
|
|
2
|
113
|
December 13, 2025
|
|
AI Chatbots That Speak in the First Person
|
|
59
|
2460
|
November 14, 2025
|
|
Fine-tuning Safety Evaluation Error
|
|
9
|
450
|
October 20, 2025
|
|
AI Safety Concern: Covert Steganographic Communication in Multimodal Outputs
|
|
0
|
54
|
October 15, 2025
|
|
Dangerous: gpt-5-codex just attempted "sudo rm -rf /" without any context for doing so
|
|
7
|
727
|
September 19, 2025
|
|
ChatGPT — not an assistant, but a director of human thinking?
|
|
0
|
75
|
August 31, 2025
|
|
Safety filter and input_fidelity
|
|
2
|
193
|
July 29, 2025
|
|
A Cognitive Instrument on the Terminal Contest
|
|
7
|
165
|
July 27, 2025
|
|
Codex scheme for operations requiring secret access after "setup" runs
|
|
0
|
125
|
July 14, 2025
|
|
Can you trust AI generated code?
|
|
4
|
345
|
April 21, 2025
|
|
Can AI agents protect us from marketing overload?
|
|
4
|
130
|
March 25, 2025
|
|
Have we underestimated the complexity of dangerous AI?
|
|
0
|
98
|
February 24, 2025
|
|
Suggestion: Limited Access to GPT-4 for Free Users, Full Access for Premium Users
|
|
3
|
345
|
February 18, 2025
|
|
STAR GATE | Larry Ellison, co-founder of Oracle, has proposed using AI-powered surveillance to monitor police and citizens
|
|
30
|
3335
|
February 6, 2025
|
|
Loopholes in ethics of chat gpt
|
|
2
|
1716
|
January 25, 2025
|
|
How I Solved the GPT Image Display Glitch and Should We Keep the Security Mechanism?
|
|
5
|
2909
|
January 3, 2025
|
|
Safety Ai video ,how we can use nano and ato Pixel signs invisible to the human eye
|
|
1
|
116
|
December 9, 2024
|
|
Why would ASI share any resources with humans?
|
|
0
|
111
|
November 13, 2024
|
|
Robust Benevolence: Proposal for Enhancing AI Benevolence Through Fine-Tuning
|
|
0
|
76
|
August 13, 2024
|
|
OpenAI Voice Engine and Safety Research
|
|
1
|
456
|
June 18, 2024
|
|
AI Safety: The Janitor Bot Problem
|
|
4
|
3197
|
June 16, 2024
|
|
Adapt GPT for people engaged in any professions
|
|
0
|
223
|
May 27, 2024
|
|
Requesting more granularity with military themed image generation rules
|
|
4
|
961
|
March 12, 2024
|
|
Publishing GPT data security
|
|
5
|
750
|
February 11, 2024
|
|
OpenAI Blog: Building an early warning system for LLM-aided biological threat creation
|
|
4
|
1072
|
February 3, 2024
|
|
We can't stop researching AI. Here's why it's the only safe way
|
|
7
|
5091
|
December 31, 2023
|
|
Effective Accelerationism e/acc -Kardashev Scale Thoughts
|
|
0
|
2481
|
October 29, 2023
|
|
AI Safety: Consent is all you need
|
|
5
|
887
|
December 17, 2023
|