Here is the summary of key improvements made:
1. Structure & Flow
- Decision Trees: Clear branching logic with ├── and └── notation
- Sequential Steps: Numbered, ordered procedures instead of scattered explanations
- Prerequisites: Explicit dependency checks before proceeding
- Tool Call Clarity: Exact function names and parameters
- Binary Decisions: Clear yes/no conditions instead of ambiguous language
- Error Handling: Specific failure conditions and next steps
- Verification Steps: "Recheck" instructions after each fix
- Reference Tables: Quick lookup for tools and purposes
- Pattern Recognition: Common issue combinations and their solutions
- Critical Reminders: Common AI mistakes section to prevent errors
- Removed verbose explanations mixed with instructions
- Consolidated multiple documents' logic into single workflows
- Used imperative commands: "Check X", "If Y then Z"
- Added immediate verification steps
Wait, are we about to reinvent programming from first principles?
Seemingly its always been on a scale between directly editing 1s and 0s and drafting legislature. Compile times may vary
I'd say it's more "programming with extra steps"
This is more like reinvention by trying everything which doesn't work first. It's the dual of first principles.
Maybe one day we will all be using https://shakespearelang.com/
I’ve found myself writing code intending to write prompts for writing better code.
Soon enough Im sure we’ll start to see programming languages that are geared towards interacting with llms
Finally a use for Lojban!
https://en.wikipedia.org/wiki/Lojban
Great! A diviner has vibe-exposed the arcane magic word knowledge on the steps to ultimate knowledgeplasty! Come let us get together to share more trial-and-error wordsmithery, Together we will someday have ultimate power!
If the model creators themselves arent sharing this magic-word bullshitteryy then why is anyone spending time on this? It is just going to change with every model release
In other words, just like programming, we’re writing better instructions. In this case, we’re asking it to think out loud more clearly. It’s almost like whiteboard interview prep.
It’s quite amazing because it means programming is fully entering the natural language phase of the timeline.
If you aren’t a solid clear writer, you may not make it in the brave new world.
>If you aren’t a solid clear writer, you may not make it in the brave new world.
Have you not heard of all the AI startups that can turn a 3-word thought into very clearly written prose to be lovingly poured into the waiting mouth of your AI agent?
Isn’t programming the clearest form of writing? Perhaps it’s the non programmers that need to “catch up”.
We are still in the pigsty compared to math
I'd have to disagree. We're much less ambiguous than math.
In fact, according to theory, we're writing executable proofs.
If programming was the most clear form of writing, then how come eductators frequently use pseudo code to make programming more clear?
The same reason kids are first taught the Bohrian atom model. It is less clear and precise, but thereby also less complex.
"100 baskets of apples" is easier to hold in your head than "23 baskets of red, small-ish apples, 12 of large red, 6 of any size green...", but my no means does it permit a more clear view of the Truth.
Different usage of the word "clear".
> Isn’t programming the clearest form of writing?
Not the way most people do it.
The computers of the future will be operated by shamans making incantations more than technicians writing code.
Of the future?
We already have people praying to the machine gods, so I guess your future is next week?