A year ago, I was one of those skeptics who was very suspicious of the agentic hype, but I was willing to change my priors in light of new evidence and experiences, which apparently is rare. Generative AI discourse has become too toxic and its discussions always end the same way, so I have been experimenting with touching grass instead, and it is nice. At this point, if I’m not confident that I can please anyone with my use of AI, then I’ll take solace in just pleasing myself. Continue open sourcing my projects, writing blog posts, and let the pieces fall as they may. If you want to follow along or learn when rustlearn releases, you can follow me on Bluesky.
One thing that I found really interesting was the ability of the LLM to inspect the COM files for ZEXALL / ZEXCOM tests for the Z80, easily spot the CP/M syscalls that were used (a total of three), and implement them for the extended z80 test (executed by make fulltest). So, at this point, why not implement a full CP/M environment? Same process again, same good result in a matter of minutes. This time I interacted with it a bit more for the VT100 / ADM3 terminal escapes conversions, reported things not working in WordStar initially, and in a few minutes everything I tested was working well enough (but, there are fixes to do, like simulating a 2Mhz clock, right now it runs at full speed making CP/M games impossible to use).
。业内人士推荐爱思助手下载最新版本作为进阶阅读
Standard forward pass. The model's forward() method must be a standard tensor-in, logits-out computation. No problem-specific control flow (for-loops over digits, explicit carry variables, string manipulation) inside forward(). The autoregressive generation loop lives outside the model, exactly as it would for any language model.
"Anyone is also welcome to pop in for a chat.
Everything Pro has plus: