Tag: Categories
-
Liberals and Conservatives See Different Victims: Moral Disagreement Is Explained by Different Assumptions of Vulnerability
all forms of judgment—including moral judgment—is a process of categorization (McHugh et al., 2022). When people wonder whether an act is immoral, they are questioning how well it belongs in the category of “immorality.” For 50 years, we have known that categorization judgments involve the process of template comparison, where our minds compare a potential example…
-
10 things I learned from burning myself out with AI coding agents – Ars Technica
with LLMs, context is everything, and in language, context changes meaning. Take the word “bank” and add the words “river” or “central” in front of it, and see how the meaning changes. In a way, words act as addresses that unlock the semantic relationships encoded in a neural network. So if you put “checkerboard” and…
-
Seven (Or, How to Play a Game Without Rules) by Joanna Kavenna
The hapless narrator’s job is to help facilitate her work in “box philosophy”: “the study of categories, the ways we organise reality into groups and sets […] the ways we end up thinking inside the box, even when we are trying to think outside the box”. https://www.theguardian.com/books/2026/jan/12/seven-by-joanna-kavenna-review-a-madcap-journey-to-the-limits-of-philosophy Sounds right up my alley!
-
How LLMs give semantic meaning to a prompt| ngrok blog
In summary, embeddings are points in n-dimensional space that you can think of as the semantic meaning of the text they represent. During training, each token gets moved within this space to be close to other, similar tokens. The more dimensions, the more complex and nuanced the LLM’s representation of each token can be. —…
-
Grokipedia Is the Antithesis of Everything That Makes Wikipedia Good, Useful, and Human
…behind the scenes, there had been robust conversation and debate by Wikipedia editors as to exactly what constitutes an “unusual” death, and that several previously listed “unusual” deaths had been deleted from the list for not being weird enough. For example: People who had been speared to death with beach umbrellas are “no longer an…
-
To really understand a concept, you have to “invent” it yourself in some capacity.
To really understand a concept, you have to “invent” it yourself in some capacity. Understanding doesn’t come from passive content consumption. It is always self-built. It is an active, high-agency, self-directed process of creating and debugging your own mental models. — Read on simonwillison.net/2025/Oct/30/francois-chollet/
-
Visual Features Across Modalities: SVG and ASCII Art Reveal Cross-Modal Understanding
We found that the same feature that activates over the eyes in an ASCII face also activates for eyes across diverse text-based modalities, including SVG code and prose in various languages. This is not limited to eyes – we found a number of cross-modal features that recognize specific concepts: from small components like mouths and…