I asked Astra to try and fix an issue in my codebase I've been battling for a month. Day and half later on high and it's still circling the drain. Seems like with each new model we praise it based on toys, but then reality hits the ground soon and we wait for the next model. In the meantime, good ol' brain.
Have you tried turning it on and off? More seriously try to remove agent memory or make it refactor it or go through the docs and look for inconsistencies.
But I still don't know how people work with codex when it keeps resetting the context so often, I mean it's surprisingly good at making notes to itself and can follow a long task, but if there are multiple instructions it sometimes forgets some of them.
I’m just trying to understand, there’s an issue you’ve been unable to deal with for a month, and Astra not being able to handle it in 36 hours is disqualifying?
On and off for a month, not straight month and not dedicated time. I am quite confident I will be able to solve it within a week or two of dedicated time. Here, on the other hand, we have this supposedly powerful thing that can do magic, unlike myself. We'll see. I'm not even confident, by looking at what it does, that it will even be able to solve it. Only thing I saw that I like is it's better in communication style compared to Fable and Opus.
I made 3D sudoku, books on paper called SUDOCUBE, with a coded index for the clues, using Opus 4.7 I think it was, which came up with the algorithm and extended my own pre-LLM Kakuro codebase:
Yeah, if it was properly 4D it would be pretty unplayable I think, you’d need 4 each 4 layer cubes, and they could not be nested in any physical configuration.
I think flipping the tiling between light and dark on the top left and the bottom right (or vice versa) would make more sense. Then bishops stay on one color and the knight always alternates between colors (like 2d chess)
Very cool! (For learning/ease of use, it would be helpful for me to be able tap enemy pieces to see where they could go next. (But with a different indicator.))
But I still don't know how people work with codex when it keeps resetting the context so often, I mean it's surprisingly good at making notes to itself and can follow a long task, but if there are multiple instructions it sometimes forgets some of them.
I liked the explanations, graphics, interactive tesseract, all nice attentions to detail.
How much guidance did you give Astra? Did you give a single prompt, an example site to mimic or was there more to the design and make process?
https://www.kakurokokoro.com/sudocube
https://csclub.uwaterloo.ca/~r345liu/
There are many, many other such games with all sorts of variations on the rules.
The reach of any embarrassing news must be limited, and there are hundreds of new AI advertisements in the pipeline that will crowd out this one.
https://en.chessbase.com/post/what-on-earth-is-5d-chess