Is the unicode really the best way to display the file structure? The special unicode characters are encoded into 2 tokens, so I doubt it would function better overall for larger repos.
Also, even if different characters were used, the 2D ascii art style representation of the directory tree in general strikes me as something that's not going to be easily interpreted by an LLM, which might not have a conception of how characters are laid out in 2D space
Loved the part at the end of the video about the Johnson-Lindenstrauss Lemma. Really great visualizations of how high dimensionality can encode so much information.
The roll outs are quite slow. Sometimes it takes weeks for them to release a feature to my account while I know others who get access immediately. I understand that it helps them control the quality of ChatGPT, but I wish I got access earlier as I have been subscribed since the beginning.
Sometimes it seems like logging off and back on causes these updates to hit. I didn't have Dall-e or image capabilities after weeks of it being released and I logged off and back on and both were available. This was between multiple computers logged in so it wasn't just a cache clearing situation.
That's an interesting idea, would be interesting to see how well it can follow the rules for creating insulation. I think one limitation would be that it is simply following predefined rules for neighboring cells, which would mean it might not produce the mathematically best result given just the neighboring cells.
Of course, it would be interesting to see all of these iterative growths from a simple set of rules.
You print the pattern on the NORMAL to the curved surface building up the cell walls... then top off with a skin.
You can modulate fillings of cells too - imagine cells being filled with anti incendiary fire retardants
or chemically induced reactionary ( so if [CHEMICAL] touches that cell, due to some sort of breach, the cell super absorbs and expands to capture that chemical...
