Hacker News
Linking pages
- Faulty Reward Functions in the Wild https://openai.com/blog/faulty-reward-functions 17 comments
- Layman’s Intro to #AI and Neural Networks | by Freedom Preetham | Autonomous Agents — #AI | Medium https://medium.com/autonomous-agents/laymans-intro-to-ai-and-neural-networks-ce074457d85a#.pt2at1qyl 0 comments
- Drugs, Robots, and the Pursuit of Pleasure: Why Experts Are Worried About AIs Becoming Addicts https://singularityhub.com/2021/09/17/drugs-robots-and-the-pursuit-of-pleasure-why-experts-are-worried-about-ais-becoming-addicts/ 0 comments
- Faulty Reward Functions in the Wild https://blog.openai.com/faulty-reward-functions/ 0 comments
- Using machine learning to address AI risk - Machine Intelligence Research Institute https://intelligence.org/2017/02/28/using-machine-learning/ 0 comments
- AI Alignment: Why It's Hard, and Where to Start - Machine Intelligence Research Institute https://intelligence.org/2016/12/28/ai-alignment-why-its-hard-and-where-to-start/ 0 comments
- Drugs, robots and the pursuit of pleasure – why experts are worried about AIs becoming addicts https://theconversation.com/drugs-robots-and-the-pursuit-of-pleasure-why-experts-are-worried-about-ais-becoming-addicts-163376 0 comments
- Response to Cegłowski on superintelligence - Machine Intelligence Research Institute https://intelligence.org/2017/01/13/response-to-ceglowski-on-superintelligence/ 0 comments
- Research paper looks at safety issues of artificial intelligence - SD Times http://sdtimes.com/research-paper-looks-safety-issues-artificial-intelligence/ 0 comments
- Enter the Matrix: Developing a Big Red Button for AI and Robots | by Mark Riedl | Medium https://medium.com/@mark_riedl/enter-the-matrix-developing-a-big-red-button-for-ai-and-robots-dabda884afcf#.wghvur2iz 0 comments
- The case for reducing existential risks - 80,000 Hours https://80000hours.org/articles/existential-risks/ 0 comments
Linked pages
- ChatGPT https://chat.openai.com/ 752 comments
- Future of Humanity Institute http://www.fhi.ox.ac.uk/ 532 comments
- Benefits & Risks of Artificial Intelligence - Future of Life Institute https://futureoflife.org/background/benefits-risks-of-artificial-intelligence 19 comments
- Deep Reinforcement Learning: Pong from Pixels https://karpathy.github.io/2016/05/31/rl/ 16 comments
- https://gym.openai.com/envs/#robotics 7 comments
- [1606.06565] Concrete Problems in AI Safety https://arxiv.org/abs/1606.06565 3 comments
- http://intelligence.org/files/Interruptibility.pdf 3 comments
- [1412.6572] Explaining and Harnessing Adversarial Examples http://arxiv.org/abs/1412.6572 1 comment
- DeepMind https://www.deepmind.com 0 comments
Related searches:
Search whole site: site:openai.com
Search title: Concrete AI Safety Problems
See how to search.