Ideas & society2016 · shared on Hacker News
Concrete Problems in AI Safety
Explore Concrete Problems in AI Safety, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yaston ·
Concrete AI Safety Problems
221 points94 comments
Yapathy ·
Simple questions to help reduce AI hype
208 points33 comments
Ysurprisetalk ·
Our position on open-weights models
191 points174 comments
Ydnetesn ·
The Last Invention of Man
172 points118 comments
Yvulkd ·
Anthropic AI
128 points25 comments
Yaburan28 ·
OpenAI Research
124 points22 comments
YBenjaminTodd ·
The world’s biggest problems and why they’re not what first comes to mind
103 points122 comments
Yyigitdemirag ·
Safety Gym
78 points17 comments
Ypde3 ·
SafeLife: AI Safety Environments Based on Conway's Game of Life
71 points12 comments
Ylyavin ·
OpenAI's Researchers: Protecting Against AI’s Existential Threat
60 points59 comments
Yad8e ·
Did Anthropic ask for this?
49 points16 comments
Ythrowaway40199 ·
Ask HN: Examples of AI ethical principles?
39 points27 comments
Ysonabinu ·
Concrete Problems in AI Safety
17 points3 comments
Ygeorgehill ·
Yann LeCun and Andrew Ng: Why the 6-Month AI Pause Is a Bad Idea [video]
12 points1 comments
Ypramodbiligiri ·
Unsolved Problems in ML Safety
3 points0 comments
Yguiambros ·
Concrete Problems in AI Safety
2 points0 comments
Yblacksmythe ·
AI Safety: problem of accidents in machine learning systems
2 points0 comments
Ypeterkshultz ·
Concrete Problems in AI Safety
1 points0 comments