Hacker News
- AI Alignment: An Engineering Problem, Not an Existential Crisis https://aalokbhattacharya.substack.com/p/ai-alignment-an-engineering-problem 0 comments
Linked pages
- A US government study confirms most face recognition systems are racist | MIT Technology Review https://www.technologyreview.com/2019/12/20/79/ai-face-recognition-racist-us-government-nist-study/ 67 comments
- Breaking into the black box of artificial intelligence https://www.nature.com/articles/d41586-022-00858-1 25 comments
- [2403.04121] Can Large Language Models Reason and Plan? https://arxiv.org/abs/2403.04121 3 comments
- [2310.19852] AI Alignment: A Comprehensive Survey https://arxiv.org/abs/2310.19852 1 comment
- [2209.13085] Defining and Characterizing Reward Hacking https://arxiv.org/abs/2209.13085 1 comment
- [2206.13353] Is Power-Seeking AI an Existential Risk? https://arxiv.org/abs/2206.13353 0 comments
- Will AI’s huge energy demands spur a nuclear renaissance? https://www.nature.com/articles/d41586-024-03490-3 0 comments
Related searches:
Search whole site: site:aalokbhattacharya.substack.com
Search title: AI Alignment: An Engineering Problem, Not an Existential Crisis
See how to search.