Equational

Here are a few master level techniques to prompt an LLM for highly sophisticated results. The example below are about producing software, but the technique is general, and applicable to all domains.  Do not start with previously written prompts that setup a generic set of rules. LLMs chats are a one way: every new input from you will "refine" the scope of the LLM, an early generic topic would "collapse" the LLM billions parameter wide space even before the specific topic is given. Start by asking for something general with regards to your final goals. You want the larger scope of the LLM to refine in the context of your end goals. For example prompt: You are probably aware of the type inference algorithm called something like cartesian product?  Start by asking in the most broad manner. Failing to be broad will refine the LLM's scope before you can use it to your full benefit. Always reformulate the LLM's response back to the LLM to fit your goals and ensure...

I spent two days last week reinstalling Nixos "bottom up", with X11 and i3. During day two I was thinking "this is such a waste of time". However it was not, here is why: Learning is about doing, and often in software that means "type it in yourself". Therefore, to install NixOS this time on a laptop, I typed everything in: the disk partitions, LUKS keys, grub setup, and new configuration file with X11 specs. I am a better developers when the system I develop on feels "simple and clear" because I configured it. I bring up this experience to share a few things. The first is that being a developer is both about being stubborn in a smart way, and about accepting loss gracefully. For example: What to do when you are locked out because somehow when you changed your LUKS keys you "screwed up"? You just reinstall again, and zenfully accept the loss of time for not being careful. What to do when you insistently fail to try to avoid to depend on...