Introducing MindMint, and its first null result
A research studio for training unusual neural networks under oversight from their first step, the wider program it serves, and a first experiment in which four expert networks learned nothing from talking to each other.
What changed this week: three new papers, a withheld shelf, and a result that didn't work
The research series grows to nine documents, three of them withheld for safety; the hypothesis page now carries the program's own objections; and a first look at subtracting training from a model's weights.
Introducing XonTools: a hypothesis, six documents, and every result so far
What this site is, what the research program is testing, what has worked, what hasn't, and what comes next.