The 13x13 grid became 14x14. It's really hard to get image models to make a board with the correct number of evenly spaced lines and star points. I'd thought it might copy a reference board into a scene, but it can't even do a simple copy, showing limits to guidance that's possible with this model.
03.05.2025 10:25 —
👍 1
🔁 0
💬 0
📌 0
A screenshot of a virtual 13x13 go board with some go stones on it.
ChatGPT's reconstruction of a 13x13 go board is actually 14x14 and it has changed the configuration of the stones.
Image models struggle to create Go boards correctly. I thought ChatGPT may be able to copy a correct one into a scene, but conditioning the model is through too small a bottleneck. "Please copy this image exactly to create a new image. Every line and stone should appear in exactly the same places."
02.05.2025 17:23 —
👍 15
🔁 1
💬 1
📌 0
Standard normalizing flows are "approximate" too: e.g., standard implementations are often not exactly invertible in practice. But ODE solvers can use adaptive computations to control the errors. So they're not intractable in the same way that (say) a Boltzmann machine is.
29.11.2024 17:00 —
👍 9
🔁 0
💬 1
📌 0
@ramandutt4.bsky.social 👋
20.11.2024 20:00 —
👍 3
🔁 0
💬 2
📌 0
I do ML + Bayesian inference.
18.11.2024 18:15 —
👍 10
🔁 0
💬 0
📌 1
