Event designators have been hiding in not-so-plain-sight since the late 1970s — so powerful that forgetting might be part of a massive conspiracy to wear out developer keyboards faster than otherwise.
The Accidental History of the @ Symbol
Once a rarely used key on the typewriter, the graceful character has become the very symbol of modern electronic communication
Shane Littrell, PhD on Twitter / X
One of the red flags of AI-written text is the heavy use of these odd linguistic constructions called “cataphoric teasers” to create an artificial feeling of suspense. These are easy to spot because they usually take the form of phrases like, “Here’s the part that nobody tells… https://t.co/kT4jRUh13x— Shane Littrell, PhD (@MetacogniShane) August 26, 2026
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.
Typing without having to type
25+ years into my career as a programmer I think I may finally be coming around to preferring type hints or even strong typing. I resisted those in the past …
The LLMentalist Effect: how chat-based Large Language Models rep…
The new era of tech seems to be built on superstitious behaviour
starship/starship
☄🌌️ The minimal, blazing-fast, and infinitely customizable prompt for any shell!
Using Claude Code: The Unreasonable Effectiveness of HTML
Thought-provoking piece by Thariq Shihipar (on the Claude Code team at Anthropic) advocating for HTML over Markdown as an output format to request from Claude. The article is crammed with …
Using Claude Code: The Unreasonable Effectiveness of HTML
Thought-provoking piece by Thariq Shihipar (on the Claude Code team at Anthropic) advocating for HTML over Markdown as an output format to request from Claude. The article is crammed with …
The Emacsification of Software
We’re all reading a ton of Markdown. It’s been the lingua franca of software development since long before LLMs. But now agents have led us into a cursed renaissance of TUI tooling, and the reading experience has become intolerable. I’m certain that at least 14% of the agita about AI code is driven by exhaustion over incessantly scrolling terminal Markdown.
The 40 Most Rage-Inducing Problems in Tech
The bugs, broken apps, and nightmare customer-service bots we can't escape, presented as a blessed and sacred addendum to Pope Leo XIV’s new encyclical on AI
Clarifying: I feel like we just invented email addresses. And they’re tricky, I get it. But I’m pushing back on “wtf is the @ symbol even, nobody knows what ‘inbox’ or ‘smtp’ is, stop making it hard for normies” Instead of making atproto invisible, what if we made it worth the learning curve?
Eli Mallon
If your goal is to make atproto accessible to non-technical users I implore you to stop calling them “normies”
Don't want to start Discourse, but tbh it kinda annoys me when every time something is launched here, some people complain: meh, this is stupid, bad design, vibe coded, you can tell by the colors it's from Claude, it relies on app.bsky lexicons, still uses Bluesky AppView, not decentralized enough,
Notation as a Tool of Thought
Notation is not a way of writing thoughts down — it is a technology that determines which thoughts are available to be had. Starting from Iverson's 1979 Turing Award lecture, this collection gathers the argument's ancestors, elaborations, and its opponents: Nielsen and Matuschak on media as cognitive infrastructure, Bret Victor's case against symbol manipulation, and empirical work on representation as a cognitive tool. Open to contributions.
The Technological Turn in Mathematics
J Notation as a Tool of Thought
Prof. Judy Fan: Cognitive Tools for Making the Invisible Visible
Media for Thinking the Unthinkable
Kill Math
Using spaced repetition systems to see through a piece of mathematics
