logoalt Hacker News

fl1pper • today at 6:33 PM • 0 replies • view on HN

The paper states that this approach doesn't use backpropagation, an optimizer, or a parameter-fitting loop.

What makes it work is that it reads its own hidden states and weight matrices -> then writes a few-line Python script to fix the weights directly (within a 20-forward-pass budget, so it can't just brute-force guesses).

After skimming through the paper and comparing it with how SEAL works (where the model still relies on RL and gradient descent to apply its self-edits), I understood it something like that :)

But I think there are comments in the thread that explain the main concept far better than I do.