Hacker News
- AI Is Too Unpredictable to Behave According to Human Goals https://www.scientificamerican.com/article/ai-is-too-unpredictable-to-behave-according-to-human-goals/ 1 comment
Linked pages
- Research AI model unexpectedly modified its own code to extend runtime | Ars Technica https://arstechnica.com/information-technology/2024/08/research-ai-model-unexpectedly-modified-its-own-code-to-extend-runtime/ 317 comments
- Google AI chatbot responds with a threatening message: "Human … Please die." - CBS News https://www.cbsnews.com/news/google-ai-chatbot-threatening-message-human-please-die/ 304 comments
- AI Spending To Exceed A Quarter Trillion Next Year https://www.forbes.com/sites/bethkindig/2024/11/14/ai-spending-to-exceed-a-quarter-trillion-next-year/ 257 comments
- https://www.pnas.org/doi/full/10.1073/pnas.2317967121 79 comments
- [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training https://arxiv.org/abs/2401.05566 18 comments
- Users Say Microsoft's AI Has Alternate Personality as Godlike AGI That Demands to Be Worshipped https://futurism.com/microsoft-copilot-alter-egos 12 comments
- Mapping the Mind of a Large Language Model \ Anthropic https://www.anthropic.com/research/mapping-mind-language-model 12 comments
- I, Robot (2004) - IMDb http://www.imdb.com/title/tt0343818/ 5 comments
- [2305.20050] Let's Verify Step by Step https://arxiv.org/abs/2305.20050 3 comments
- Microsoft AI chatbot threatens to expose personal info and ruin a user's reputation | Fox Business https://www.foxbusiness.com/technology/microsoft-ai-chatbot-threatens-expose-personal-info-ruin-users-reputation 1 comment
- A Viral Game About Paperclips Teaches You to Be a World-Killing AI | WIRED https://www.wired.com/story/the-way-the-world-ends-not-with-a-bang-but-a-paperclip/ 0 comments
- The Year Chatbots Were Tamed - The New York Times https://www.nytimes.com/2024/02/14/technology/chatbots-sydney-tamed.html 0 comments
Related searches:
Search whole site: site:www.scientificamerican.com
Search title: AI Is Too Unpredictable to Behave According to Human Goals | Scientific American
See how to search.