Jordan Rubin: "A library you can import through the right metaphor"
...mport through the right metaphor" The right jargon unlocks the right library of background context. LLMs understand almost all jargon.
Topic: background context
12 chunks · 9 episodes
Topic summary
?
A short read on the topic's time range, peak episode, and strongest associations. Use it as the quick orientation before drilling into examples.
- background context appears in 12 chunks across 9 episodes, from 2024-01-16 to 2025-09-15.
- Its densest episode is Bits and Bobs 12/2/24 (2024-12-02), with 4 observations on this topic.
- Semantically it travels with llms, bobs, and bits, while by chunk count it sits between Ben Thompson and excellent piece; its yearly rank moved from #72 in 2024 to #178 in 2025.
Over time
?
Raw mentions over time. Use this to see absolute attention, not relative rank among all topics.
Observations
?
The primary evidence view for this topic. Sort it chronologically when you want concrete examples behind the larger pattern.
I built a chatbot into my https://thecompendium.cards.
... week. In the past I've found being able to pass the Bits and Bobs to Claude as background context made it a much more powerful brainstorming partner. But recently the amount of Bits and Bobs–even just focusing on the ones related to my job–was far...
Hyper concentrated insight is now more valuable than before because it can be diluted by LLMs.
... media. This is one of the reasons my Bits and Bobs export is such an effective background context[vv] for me to feed to LLMs when I'm brainstorming.[vw] My Bits and Bobs is like my own personal intellectual orange juice concentrate.
Chats are append-only logs of messages because it's hard for the human to absorb changes in the conversation.
...totally can go back and amend, tweak, edit the previous messages to give better background context.
LLMs compress nearly all of humanity's background context into a teensy weeny little hyperobject package.
LLMs compress nearly all of humanity's background context into a teensy weeny little hyperobject package. They have effectively infinite background context–a marvel of lossy compression. The answers to innum...
A RAG approach is kind of like Shark DNA vs Frog DNA.
...ke Shark DNA vs Frog DNA. 'Frog DNA' is the generic mush the model learned, the background context it falls back on to fill in the gaps that you didn't specify in your prompt. With RAG you proactively select the most useful bits for it to use to fi...
How many thousands of papers in the 70's, 80's, 90's, and 2000's had great ideas that were just ahead of their time?
...How many of them hit a wall needing some kind of hyperobject with near infinite background context? If you sprinkle the pixie dust of LLMs on those old ideas, how many could spring to life?
A Small Matter of Programming is a classic book focused on how to create malleable tools that normal users can understand and build: end-user programming.
...resentation to allow this to be feasible." You'd somehow need all of humanity's background context compressed into a tiny little hyperobject that you could cheaply, easily, and quickly query with arbitrary questions. Hmmmm….
What counts as MAYA has to do with the background context.
What counts as MAYA has to do with the background context. For example, if you tried to introduce jazz in 1850 it would have been rejected. Jazz is a speciation event in a coevolutionary space. It required a...
A year ago: "Who could ever need more than 200,000 tokens???"
...on length limits in my Claude chats that use projects that I've crammed full of background context. LLMs do better the more context they have to work with. People will cram contexts as full as the LLM will let them.
Illegible + open gives you capped downside while retaining exposure to upside.
...xplainers or READMEs. Have documentation in a Google Doc, not a website. Assume background context the reader might not have. Connect nine of the ten dots. Hide signal in a swarm of interesting but distracting details.
In my knowledge management workflow, I interact with notes three times:
...dd a teensy bit more context to help the idea make sense in the future once the background context is lost, develop the idea just a teensy bit, and maybe interlink with other recent related ideas. A lot of the time, similar ideas have come up in mu...