Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		www.alignmentforum.org Debating with More Persuasive LLMs Leads to More Truthful Answers - AI Alignment Forum
\|	\|	www.lesswrong.com OpenAI's Alignment Plans - LessWrong	3.4 parsecs away Travel
\|	\|	Our alignment research aims to make artificial general intelligence (AGI) aligned with human values and follow human intent. We take an iterative, em...	3.4 parsecs away Travel
\|	\|	distill.pub AI Safety Needs Social Scientists	3.1 parsecs away Travel
\|	\|	If we want to train AI to do what humans want, we need to study humans.	3.1 parsecs away Travel
\|	\|	www.lesswrong.com Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training - LessWrong	3.8 parsecs away Travel
\|	\|	I'm not going to add a bunch of commentary here on top of what we've already put out, since we've put a lot of effort into the paper itself, and I'd...	3.8 parsecs away Travel
\|	\|	metasd.com AI for modeling - what (not) to do - MetaSD	24.3 parsecs away Travel
\|		Ali Akhavan and Mohammad Jalali have a nice new article in the SDR on the use of AI (LLMs) to complement simulation modeling. Generative AI and simulation modeling: how should you (not) use large language models like ChatGPT Ali Akhavan,Mohammad S. Jalali Abstract Generative Artificial Intelligence (AI) tools, such as Large Language Models (LLMs) and ... Continue reading "AI for modeling - what (not) to do"	24.3 parsecs away Travel