/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
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover - AI Alignment Forum
| | www.cold-takes.com
Why Would AI "Aim" To Defeat Humanity?
2.8 parsecs away

Travel
| | Today's AI development methods risk training AIs to be deceptive, manipulative and ambitious. This might not be easy to fix as it comes up.
| | www.cold-takes.com
Forecasting transformative AI: the "biological anchors" method in a nutshell
4.1 parsecs away

Travel
| | My preferred method of forecasting transformative AI, with pros and cons.
| | blog.jessriedel.com
Notable reviews of arguments for AGI ruin - foreXiv
2.9 parsecs away

Travel
| | Here's a collection of reviews of the arguments that artificial general intelligence represents an existential risk to humanity. They vary greatly in length and style. I may update this from time to time. (This is well-paired with Katja Grace's summary of counterarguments.) Continue reading
| | www.tomsguide.com
Google Gemini just got 3 big upgrades after surpassing ChatGPT in App Store | Tom's Guide
22.2 parsecs away

Travel
| Google's September update for Gemini adds plenty of new features that make its popular AI model even smarter. Here are the three biggest upgrades coming to Gemini.