LLMs are really good at absorbing infodumps.
LLMs are really good at absorbing infodumps. You don't need a ton of structure for the LLM to get it. Humans are way worse at receiving infodumps. They ge...
Topic: llms
1,841 mentions · 834 chunks · 141 episodes
194.1× distinctiveness vs baseline
?
How much more common this term is here than in ordinary English. Higher values mean the topic is more characteristic of this corpus.
1.6x burst in 2025 Q1
?
Peak quarter intensity across the topic's active span. Higher values mean attention was concentrated into a shorter stretch rather than spread evenly over time.
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.
- llms appears in 834 chunks across 141 episodes, from 2023-11-06 to 2026-10-12.
- Its densest episode is Bits and Bobs 10/20/25 (2025-10-20), with 17 observations on this topic.
- Semantically it travels with Claude, ChatGPT, and Meta, while by chunk count it sits between Claude; its yearly rank moved from #2 in 2023 to #1 in 2026.
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.
If LLMs are like electricity, we should use them to electrify software.
If LLMs are like electricity, we should use them to electrify software.
Refactors that go for more than a month are always a disaster.
... politics of multiple distractible humans with their own incentives because the LLMs will just execute on the plan with infinite patience. So you get 10x productivity without 10x the coordination cost.
LLMs will find workarounds to achieve the goals you set.
LLMs will find workarounds to achieve the goals you set. That implies that you need to give them lots of tests. But often the agents also create the tests...
The key question: will LLMs just compound crap code quickly, or will it accumulate and accrete in useful ways?
The key question: will LLMs just compound crap code quickly, or will it accumulate and accrete in useful ways? Will code get so unworkable that it collapses under its own weight...
We're still driving around in horse and buggy, with a racecar in the garage.
...egrate into our lives. Today we've only integrated chatbots into our lives. But LLMs are so much more powerful than that.
Explore has gotten way cheaper than exploit.
... cheaper than exploit. That happens when any new input changes. It's less about LLMs being great at explore (though that's part of it). It's mainly that LLMs are ushering in a new paradigm.
When the cost of inputs decreases by an order of magnitude, it leads to a cambrian explosion.
...ings. So the explosion is the immaturity of the space more than fundamentals of LLMs.
LLMs are clearly useful… and also the things people use them for are the dumbest things.
LLMs are clearly useful… and also the things people use them for are the dumbest things.
I love LLMs and I hate chatbots.
I love LLMs and I hate chatbots. I think chatbots are an embarrassing party trick. Corporations pretending to be our friends. Depressingly, this is all people th...
Anyone can hit the photocopy button to have LLMs make slop.
Anyone can hit the photocopy button to have LLMs make slop. The most valuable thing is having the taste of which subset is actually useful[ds].
LLMs are gap-fillers and will fill all gaps implicitly with the most average input.
LLMs are gap-fillers and will fill all gaps implicitly with the most average input. So it's your job to give them non-average gaps to fill, to inject the ...
A new important word in the era of LLMs: elevated.
A new important word in the era of LLMs: elevated. What makes you as a human special when I can replace you with a script?
Elevated and amplification are two related words around use of LLMs.
Elevated and amplification are two related words around use of LLMs. LLMs amplify whatever you apply them to. You can apply them to something good or bad. For example, curiosity vs laziness. But elevated implies the r...
Jargon that is understood by your collaborator is like a magic incantation.
...on. It has to be understood by your collaborator to actually give you leverage. LLMs are great at unpacking any jargon.
Industrialization loses the craft.
...eeling of ennui develops. Simon Willison calls this, in the context of SWEs and LLMs, "deep blue."
It used to be the writer, the athlete, the actor, that we elevated.
...t used to be the writer, the athlete, the actor, that we elevated. But now with LLMs it will be the editor, the coach, the director who matter most.
There's a difference between vibecoding and Elevated Engineering.
There's a difference between vibecoding and Elevated Engineering. Both use LLMs in new ways. Vibecoding is a "make it work" mindset. A good enough, satisficing mindset. Elevated Engineering uses LLMs to extend your expertise. For...
How will LLMs affect open source quality?
How will LLMs affect open source quality? It definitely undermines the business models of e.g. Tailwind. Those models are unlikely to ever work again. But now engi...
LLMs are the best tech in the world to cheat at homework...
LLMs are the best tech in the world to cheat at homework... and simultaneously, the best tech in the world to learn new things. Is your default tendency l...