Explore >> Select a destination
|
You are here 
|
www.jefftk.com | ||
| | | | |
www.alignmentforum.org
|
|
| | | | | Consider the following scenario: ? * We have ideas for training aligned AI, but they're mostly bad: 90% of the time, if we train an AI using a rando... | |
| | | | |
www.alignmentforum.org
|
|
| | | | | You want your proposal for an AI to be robust to changes in its level of capabilities. It should be robust to the AI's capabilities scaling up, and a... | |
| | | | |
www.alignmentforum.org
|
|
| | | | | tl;dr: We fine-tune or few-shot LLMs to use reasoning encoded with simple ciphers (e.g. base64, rot13, putting a dot between each letter) to solve ma... | |
| | | | |
jimmeruk.com
|
|
| | | [AI summary] The post features a collage of images, likely photoshops, accompanied by the title 'Just getting it done... regardless' and a brief description about the website's cookie policy. It does not have a clear main content area that can be classified into the provided categories, but it is centered around imagery and digital content creation, aligning best with graphic art. | ||
