Description of subprojects and results, including major changes from the original proposal

Here's the second progress report; in short, we generated the intended corpus and then a second bonus "victory-lap" corpus testing the Turntrout hypothesis. Here: https://www.lesswrong.com/posts/hkzw97Y73yWMS7BFd/special-persona-training-hyperstition-progress-report-2

Spending breakdown

$5000 was a useful drop in the bucket towards generation costs of creating ~1B tokens worth of synthetic training corpora. Thank you!

What progress have you made since your last update?

Here's a corpus of 5000 novels starring a friendly helpful harmless AI as friend and confidante: https://huggingface.co/datasets/dickbutkis/hyperstition/blob/main/Hyperstition%20Corpus%20v1.zip

What are your next steps?

We're aiming to create the proposed TurnTrout/Cloud dataset, running that downstream experiment. The vision is to evade existing misalignment narratives by generating stories about a "❖", a novel type of synthetic angel being, fine-tune a model on that corpus, and prepend all future prompts with "you are a ❖" to see if we have less misbehavior.

Is there anything others could help you with?

This next dataset will cost more compute and any gifts of compute would be welcome.

Let's improve the beauty waterline!

if you think about it correctly, this is the most promising life extension angle available to us

isaak is smart, tenacious, and resourceful

no brainer; fuck it we ball