Tag
A blog post about repurposing an old ThinkPad as a dedicated writing machine running Debian and Emacs, inspired by Veronica Explains' writerdeck concept, with tips on configuration and file syncing via Git.
The user finds that using K3 as a research and first draft assistant for commercial video script writing is surprisingly effective.
A developer built a guardrail that monitors AI agent output in real-time, as it writes, rather than after completion.
Gergely Orosz tests new AI models like Fable and GPT-6 by asking them to write articles in his style from his interviews, but finds they fail spectacularly, producing lots of words without understanding.
A developer shares frustration with traditional word processors and presents an experiment to turn Typst into a WYSIWYG editor optimized for e-ink tablets, leveraging AI to generate templates from descriptions.
A Twitter user compares GLM5.2 and Deepseek V4 Pro, praising GLM5.2 for programming at near-AGI level but finding it inferior to Deepseek V4 Pro in writing, particularly for outlines and romance novels.
The author complains about severe Claude account bans, making it difficult for users to use official accounts normally. For coding, codex and glm5.2 can replace Claude, but there is no perfect substitute for writing and thinking, only deepseek and gemini barely usable.
Matt Pocock announces that his 'writing-great-skills' tool, invoked via npx, is becoming his most frequently used skill for writing skills.
The author argues that the key question about AI-generated content should not be 'did AI write this?' but rather what human judgment and taste were applied before output, emphasizing the need for context, evidence, and editorial decision-making.
An article by Robert J. Sawyer defending the use of WordStar, a classic DOS word processor, for creative writing, with testimonials from famous authors.
Paul Graham argues that in the near future, choosing not to use LLMs for writing will be uncommon but a mark of those who care about thinking clearly, warning that a divide between 'writes' and 'write-nots' will mirror a divide between 'thinks' and 'think-nots'.
A blog post warns against using LLMs to write incident reports, arguing that it bypasses the critical thinking inherent in the writing process, leading to plausible but potentially incorrect reports that evade verification.
User asks whether providing a sample of their writing style to a local LLM is more effective in the conversation or in the system prompt.
A tweet urging people to reduce their reliance on LLMs and return to long-form writing and thinking on paper to think more clearly and avoid self-deception.
A comic from the wizardzines archive that advises writing for a single person, aimed at developers and technical communicators.
A discussion on whether the increasing use of AI agents in programming, writing, and business is leading to a decline in human cognitive skills, drawing parallels to the calculator debate in the 1980s.
Discussion comparing Gemma4 12b and 26a4b variants, focusing on creative tasks like writing and chatting.
A writer questions the accuracy of AI detection tools after receiving wildly inconsistent results for her own human-written movie reviews, highlighting the unreliability of current AI checkers.
Lists 12 practical AI skill tools covering browser automation, deep research, development, design, office work, and writing, aimed at boosting worker productivity.
A pilot study with 24 college students examines how varying levels of LLM access (none, limited, unlimited) affect essay writing quality, behavior, and perceived authorship, finding that constrained access preserves authorship confidence while unlimited access reduces creative expression and ownership.