A short read on the topic's time range, peak episode, and strongest associations. Use it as the quick orientation before drilling into examples.
code written appears in 7 chunks across 6 episodes, from 2024-02-12 to 2026-01-19.
Its densest episode is Bits and Bobs 8/19/24 (2024-08-19), with 2 observations on this topic.
Semantically it travels with llms, vast majority, and black box, while by chunk count it sits between code execution and emergent force; its yearly rank moved from #110 in 2024 to #167 in 2026.
Over time
?
Raw mentions over time. Use this to see absolute attention, not relative rank among all topics.
Range2024-02-12 to 2026-01-19Mean1.2 per episodePeak2 on 2024-08-19
Observations
?
The primary evidence view for this topic. Sort it chronologically when you want concrete examples behind the larger pattern.
Showing 7 observations sorted from latest to earliest.
...n a textbook.
Truly novel Algorithmically Interesting code is maybe .01% of all code written.
Maybe 20% of code is CRUD.
Simple wrappers around SQL.
The other 80% of code is just boring integrations.
Just shuttling code back and forth between...
...le to do an auto-assembling process with code.
Writing code was too hard to do.
Code written by other anonymous creators is untrusted.
You can't run untrusted code on sensitive data.
LLMs can write code.
Now you just need a way to make runnin...
Things written by LLMs are slop.
Integration code written to combine disparate things is glue code.
Glue code written by LLMs is glop.
Glop is a kind of black box; it doesn't need to be understood necessaril...
Code written for humans to work with has to fit into a human brain's limited context window.
Which requires layers of abstraction; leverage for thinking.
A massiv...
...ion over time.
But if the value of software is the combinatorial possibility of code written by different people being composed into new wholes, then across-origin should be common.
A system that leaned into making across-origin compositions ...
Code written in the LLM era will be smaller single files, not separations of concerns. LLMs do better with smaller files with all local context.
Code that LLMs wr...
...e difference between a protocol and a platform?
Using a platform requires using code written by someone else.
It might be a tool (open source, perhaps running on your computer)
It might be a service (requiring reaching out to the code running...