I actually saw a little excerpt of a video interview that I failed to find to give you the link where he was asked about his current project. He showed a stack of cards that became Ada and talked about the main theme being passage of time
Fixed header isn't always a good thing, it can also be a mistake. Since content is the product, let the content take up all available space and use your browser navigation capabilities to navigate if necessary
Not to have him cancelled in the first place. No need to pretend that doing something under the mob pressure is the same as doing something entirely willingly
Michael Hobbes, host of IBCK is guilty of those inaccuracies too. Here's him being fact checked regarding claims in the Maintenance Phase podcast: https://spurioussemicolon.substack.com/
I get the idea of making a frankenstein computer, I just disagree that 6502 is THE platform to do it on. Practically, there's no way for me to find it. Other comment mentions ARM, which is a much more interesting proposal to me
If I scavenge any machine today, how likely would I be to find a 6502 vs something more modern? I’d argue that some people might have a NES at home and one could get a 2A03 from it, but in a hypothetical scenario where I need to scavenge some computational power, I’d find an Android phone
I tried this myself and IMO, this might be basic and day-to-day for you, with unambiguous correct paths to follow, but this is pretty niche nevertheless. LLMs thrive when there's a wealth of examples and I struggle to Google what you asked myself, meaning that LLM will perform even worse than my try.
Try this prompt: Create a detailed step by step plan to implement a boilerplate Zephyr project skeleton for Pi Pico with configured st7789 SPI display drivers
Ask Opus or Gemini 2.5 Pro to write a plan. Then ask the other to critique it and fix mistakes. Then ask Sonnet to implement