Join Notes
A batch of the best highlights from what Tristan's read, .
However, if we first ask the model to identify the language of the text, and then summarize the text, it becomes more reliable:
openai-cookbook/techniques_to_improve_reliability.md at main · openai/openai-cookbook · GitHub
https://github.com/openai/
Nevertheless, our values are still clearly relevant to these decisions about what to fund.
A Tapestry of Values
Kevin C. Elliott
And the way things are going, I can't say with confidence that mere token predictors *won't* have the ability to internally simulate agents soon. For the purposes of safety, the fact that your AGI isn't "actually" malevolent while playing a malevolent role isn't comforting.
Why I Think Strong General AI Is Coming Soon
lesswrong.com
...catch up on these, and many more highlights