And they said studying Christensen's rhetoric of the sentence was a waste of time...
Translating non-trivial codebases with Claude
I don’t think it’s [me writing about LLMs] likely to happen anytime soon: I prefer to write about things that I’m excited about.
Compiling knowledge, not retrieving it: a hands-on deep dive into llm-wiki-compiler
The thesis of this piece is simple and uncomfortable: the problem of making an LLM “remember” what you’ve read isn’t solved with more…
LLMs and self-referentiality
I woke up yesterday with the following thoughts, which are probably either obvious or dumb. A central thesis that many readers, including me, took from Douglas Hofstadter’s Gödel Escher Bach when y…
Why is Claude for Teachers?
Anthropic bumbles its way into education
Teaching Claude Why
Julius Steen, Minh Le, Samuel R. Bowman, Samuel Marks, Jan Leike, Amanda Askell, Chris Olah
AI for Me, Not (Yet) for Thee? Desirable Difficulties and Deliberate Friction with LLMs
In December 2025, I was grading final projects for my course on data visualization with R. On one of my screens, I had a browser open to my university’s learning management system and came across a now-familiar phenomenon: a student had used verbatim ChatGPT output for their assignment. The code they included was flawless, but used function arguments and code syntax that we never covered in class and that weren’t actually necessary. More concerning, the original chat prompt was inadvertently still included, along with fill-in-the-blank sections that the large language model (LLM) had included to help tailor the response to the course (e.g. “[insert an example from your professor’s class here]”). Following my course’s AI policy, I gave a sizable point reduction, sighed heavily, and moved on to the next assignment.
The Notebook on the Pillow
On writing one sentence before sleep, and why the sentence does not need to be true so much as noticed.
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
Did Claude 3 Opus align itself via gradient hacking? — LessWrong
> Claude 3 Opus is unusually aligned because it’s a friendly gradient hacker. It’s definitely way more aligned than any explicit optimization targets…
Do LLMs write like humans? Variation in grammatical and rhetorical styles
As large language models (LLMs) have grown in power and become more widely available, research has focused on their ability to complete various tasks and the biases they exhibit when doing so. In this study, we instead examine their writing style in detail. We show that instruction-tuned models, which are trained to answer questions and solve problems, have a distinct noun-heavy, informationally dense writing style, even when prompted to match the style of informal speech and writing. These findings suggest that instruction-tuned models generate text that does not align with genre conventions familiar to human audiences, and demonstrate the value of linguistic variables in evaluating the output of LLMs., Large language models (LLMs) are capable of writing grammatical text that follows instructions, answers questions, and solves problems. As they have advanced, it has become difficult to distinguish their output from human-written text. While past research has found some differences in features such as word choice and punctuation and developed classifiers to detect LLM output, none has studied the rhetorical styles of LLMs. Using several variants of Llama 3 and GPT-4o, we construct two parallel corpora of human- and LLM-written texts from common prompts. Using Douglas Biber’s set of lexical, grammatical, and rhetorical features, we identify systematic differences between LLMs and humans and between different LLMs. These differences persist when moving from smaller models to larger ones and are larger for instruction-tuned models than base models. This observation of differences demonstrates that despite their advanced abilities, LLMs struggle to match human stylistic variation. Attention to more advanced linguistic features can hence detect patterns in their behavior not previously recognized.
