Models can fit more context in their "head" in a moment than we can.
...t than we can. We can only do it with compression. There are certain tasks that LLMs can do easily that humans can't. Needle-in-a-haystack style tasks.
Topic: llms
1,690 mentions · 755 chunks · 125 episodes
179.0× 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.
1.5x 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 755 chunks across 125 episodes, from 2023-11-06 to 2026-06-15.
- Its densest episode is Bits and Bobs 10/20/25 (2025-10-20), with 17 observations on this topic.
- Semantically it travels with ChatGPT, Claude, and Google, 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.
Hierarchical Task Network Planning might finally be viable in the world of LLMs.
Hierarchical Task Network Planning might finally be viable in the world of LLMs. This was a technique I learned in my AI class in college in 2007. You take a high-level task and break it down into smaller tasks, recursively, unti...
Tokens are better spent on explore than exploit.
... better spent on explore than exploit. Exploring is about surprise, which means LLMs are great for it. Exploiting starts off being about surprise, but as it gets dialed in on a given hill, becomes about efficiency. Mechanistic softwar...
Giving the right context to LLMs is such a powerful unlock that it feels like cheating.
Giving the right context to LLMs is such a powerful unlock that it feels like cheating. They're a steam engine, just fill them with the right fuel and they can move mountains.
One of the things that kicked off the era of Agentic Engineering was just robust file editing.
...ntic Engineering was just robust file editing. As recently as a few months ago, LLMs editing files was error-prone and slow. Streaming out an edited file, token by token, and hoping the LLM doesn't get confused or try to 'improve' som...
LLMs have only been getting incrementally better but new things are also made discontinuously possible.
LLMs have only been getting incrementally better but new things are also made discontinuously possible. That's due to threshold effects. Some use cases do...
A paper: Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability.
...s: Permuted Congruential Generators, Curricula, and Interpretability. Turns out LLMs are very good at learning the patterns underlying any sequence, no matter how subtle.
A continual process for managing a resonant spec for a product.
...re the artifact is default-converging. Useful for human teams… and working with LLMs too!
Massively subsidized tokens have distorted AI demand.
...ed to Claude in a loop instead of python and bash scripts to do routine tasks." LLMs are insanely powerful and able to handle surprise in a way mechanistic software never could. But they are ludicrous overkill for most tasks. If you h...
LLMs are explosively valuable in the domain of code.
LLMs are explosively valuable in the domain of code. Is it because code is the first domain to explode… or is there something about LLMs being a perfect f...
Code is now cheap, but making software that actually works is still expensive.
... a logarithmic curve to quality. What looks 80% done is 20% done. Building with LLMs allows getting superficial results extremely quickly. But it doesn't get that last 80% done unless you hound it to go into the details that you haven...
A class of engineers that are about to have a very hard time: those who are "below LLM replacement level."
...re about to have a very hard time: those who are "below LLM replacement level." LLMs have already become much better engineers than the vast majority of us. The only way to stay above water is to learn new ways of working that take ad...
A small prompting trick: append "dozo".
...but a bit passive aggressive. "Yes, of course, why are you asking, just do it." LLMs know the connotations of that word and respond appropriately.
The AI Peter Principle is even stronger than the original.
The AI Peter Principle is even stronger than the original. LLMs allow you to execute beyond your ability. The result is you're almost certainly out over your skis. You could stop within your ability, but humans ar...
Incoherence is viral.
...rging requires a process that reduces incoherence over time, that roots it out. LLMs have infinite patience[c] but are also prone to introduce subtle mistakes.
LLMs have the advantage in any domain where patience is more valuable than taste.
LLMs have the advantage in any domain where patience is more valuable than taste.
LLMs are fundamentally naive.
LLMs are fundamentally naive. Prompt Injection is just the most extreme version of that. But LLMs do subtly dumb things all the time. The practical risk o...
LLMs are like oxidation is for life.
LLMs are like oxidation is for life. Critical and yet not sufficient. The force needs to be harnessed in the right structure to unleash its power in coher...
Race-to-the-middle advice can only ever make you good, never great.
...to-the-middle advice can only ever make you good, never great. McKinsey is like LLMs, in that they both give you advice that will help you race to the middle.
We've been living in the era of the knowledge worker.
... world. Of course the best jobs are knowledge work, and always will be. But now LLMs can do cognitive labor at an unimaginable scale. …Maybe knowledge work won't be as common, or often will take a different form?