A kind of odd mental model for storing state in a system.
A kind of odd mental model for storing state in a system. Pure functions that take inputs and produce outputs. To store state, loop back function's output to the inputs of a ne...
Topic: mental model
79 chunks · 60 episodes
2.0x 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.
- mental model appears in 79 chunks across 60 episodes, from 2023-10-09 to 2026-07-27.
- Its densest episode is Bits and Bobs 3/10/25 (2025-03-10), with 4 observations on this topic.
- Semantically it travels with ground truth, early adopter, and ChatGPT, while by chunk count it sits between ground truth and schelling point; its yearly rank moved from #3 in 2023 to #14 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.
Another puzzle of LLMs: they're surprisingly bad at generating very large legal JSON blobs.
...large legal JSON blobs. They'll often miss a comma or a } or ]. This breaks our mental model; they're so good at generating things that match even subtle patterns, and this is something a simple pushdown automata could handle! LLMs are not do...
LLM: A mind of a toddler who has also read every book in the world.
...s, we don't have any points of reference for it. We get tricked by an erroneous mental model of what it can and cannot do.
Observation is inherently noisy.
...ils matter and which can be ignored is an act of judgment. It requires having a mental model of what you expect, so you can see the things that don't fit the model (and are thus important to attend to). This is one reason why observing the wh...
When your users do something that surprises you, investigate.
...mething that surprises you, investigate. The fact you're surprised implies your mental model of what they want is wrong.
Apps are hard.
... to melt to interact with the softness of LLMs. A mini app is still an app-like mental model. Too hard for this new era. Sand is hard but only at the micro level. At the macro level it's soft. The hardness is on such a small scale that it's n...
A goal in any system: minimize nasty surprises.
... nasty surprise. A nasty surprise is something that violates the user's implied mental model, and might cause them to never want to use the service again. When you're developing a new assistive service, you want to minimize how many people ha...
Every context becomes a bit of an echo chamber.
...ironment might become "old money". If something new comes along that breaks the mental models, it simply won't fit! The Silicon Valley tech scene is heavily optimized for this late stage vertical Saas world.
Things that are illegible to you are moving along a dimension you can't see.
...ate the nuance. Weird things will happen that you cannot fit into your existing mental models in any way. It's like living in flatland and seeing a sphere: "Wait, how is that circle getting smaller and then bigger? What the heck?
Mass market users almost never think about security or privacy models.
... models. What's the last time you thought about the same-origin model, the fundamental model that underlies the web and modern apps' laws of physics? The inductive willingness of less-savvy people to trust a security model is about iterative ...
Stray thoughts on LLMs.
...ut before the sense making happened. That creates a lot of chaos and swirl. The mental model for what it is hasn't fully emerged out of collective tinkering yet.
We maintain mental models of the systems that we interact with that can be wrong, and sometimes confuse us.
We maintain mental models of the systems that we interact with that can be wrong, and sometimes confuse us. Matt Webb told me he had heard somewhere that humans tend to categ...
Let's pull on a thread starting from the observation that LLMs only "think" one token at a time.
...get the illusion of a pre-planned result, when it really wasn't at all. Another mental model: LLMs are like the main character in memento. The main character "wakes up", sees the tattoos and the sticky notes, and says "well I guess the next s...
"Wrinkling your brain" is "adding complications to your previously overly simplistic mental model"
...kling your brain" is "adding complications to your previously overly simplistic mental model" Wrinkling something makes it more nuanced, more complex, more capable of handling subtlety. Fractally-wrinkled things are more resilient. You can't ...
Don't spend time thinking about the boring things.
... the boring things. Boring things here means, "unsurprising", which means "your mental model is sufficiently calibrated to correctly predict its output in practice" For boring things, automate them. Get to good enough and don't overthink it. ...
It's hard to understand how a black box works.
...t's hard to understand how a black box works. You understand a system when your mental model can accurately predict what it will do in response to most inputs. With a black box you don't know what state it's in at any given point and have to ...
Good epistemic hygiene is not "write a lot of docs" and "do every analysis down to minute detail in triplicate."
...n triplicate." It's "humbly seek disconfirming evidence and absorb it into your mental model, and don't waste time chasing down the illusion of certainty".
Imagine two discussion participants.
...things they fundamentally disagree on--that are so outside each others' current mental model that they track as incomprehensible noise or actively clash--then they'll lose trust and come out of the conversation with nothing to show for it. Th...
Games are magic at building up knowhow.
...make active decisions. To take actions means they have to be engaged and have a mental model of the situation. Building a robust, useful mental model is what builds knowhow. So games create knowhow as a kind of byproduct, and that byproduct c...