Tropes.fyi – Name and shame AI writing
Today I come to you on this beautiful Friday with a freshly hardthink-ed solution to a proliferous problem plaguing our world: the loss of original voice. The blanket of blandness slowly suffocating centuries of writing. Or to put it bluntly: AI writing is trash. It is disrespectful to expect ME to read something YOU could not even be bothered to write (or likely even read). The lingering human connection that remained resilient on the internet - through years of SEO optimisation, propaganda bots, ads, regional firewalls, politics, censorship - is now being diluted even further. Many of the…
What it does
In the maker’s words, at launch
Today I come to you on this beautiful Friday with a freshly hardthink-ed solution to a proliferous problem plaguing our world: the loss of original voice. The blanket of blandness slowly suffocating centuries of writing. Or to put it bluntly: AI writing is trash. It is disrespectful to expect ME to read something YOU could not even be bothered to write (or likely even read). The lingering human connection that remained resilient on the internet - through years of SEO optimisation, propaganda bots, ads, regional firewalls, politics, censorship - is now being diluted even further. Many of the posts I eagerly click on HN (especially sorting by new) are now disappointingly, ragingly, completely AI generated. This includes several that reach the front page on a daily basis. It's shameless. Unfortunately, many of you educated readers are oblivious to the tropes and tells or too eager to discuss the topic to notice. To combat this (and because I'm petty) I (and ironically Claude) built a directory and several tools to name and shame these patterns. Both to educate those are not AI-literate and to spread awareness. NOT TO HARASS. tropes.fyi is a catalogue of the recurring tropes, tics, structures and word choices that give away AI-generated writing. Each trope is documented with a name, description, real-world examples and the category it falls under (word choice, sentence structure, tone, formatting, composition). There are currently 32 tropes. Some highlights: - Negative Parallelism: "It's not X — it's Y." The SINGLE MOST COMMON AI writing tell. One per piece is fine. Ten in a blog post is insulting. AND I HAVE SEEN TEN IN A BLOG POST. - Tricolon Abuse: The compulsive rule of three. "Products impress people; platforms empower them. Products solve problems; platforms create worlds." - Em-Dash Addiction: A beautiful punctuation. Once the sign of a brilliant writer now too many of these is a red flag. I still use them, you won't break my spirit. - "Delve" and Friends: Perhaps the most infamous. "Delve" went from uncommon to appearing in a staggering percentage of AI text. See also: "leverage", "robust", "harness". full directory: https://tropes.fyi/directory ai;dr - Paste a link to any article. It will strip the AI fluff using our trope detection rules, then feed the skeleton to a lightweight llm which reverse-engineers it back to the prompt they likely* typed :D. 3000 words of slop → 30-word prompt + whatever unique insights (if any) survived the bloat. try it: https://tropes.fyi/aidr AI Vetter - Paste a URL, get a verdict. The AI Vetter fetches article content, runs rule-based pattern matching against all 32 tropes and returns a score on the scale: Human → AI-assisted → Suspicious → Barely Legible → Pure AI Slop. try it: https://tropes.fyi/vetter tropes.md - A single file you can drop into any AI assistant's system prompt so it avoids these patterns. Sorry for helping them become invisible, I'd just rather not see it. "You're a hypocrite I'm sure you use AI for writing code!" — AI generated code is fine, it's one computer (LLM) talking to another (compiler). How else do you think AI is so good at writing code? They're speaking the same language! But prose? That's from human to human, it's sacred and meant for other people. Using AI for that is deceitful.
Does the same job
all alternatives →- WFWe fingerprinted 178 AI models' writing styles and similarity clustersApr 2026 · rival.tips · ▲78
We have a dataset of 3,095 standardized AI responses across 43 prompts. From each response, we extract a 32-dimension stylometric fingerprint (lexical richness, sentence structure, punctuation habits, formatting patterns, discourse markers). Some findings: - 9 clone clusters (>90% cosine similarity on z-normalized feature vectors) - Mistral Large 2 and Large 3 2512 score 84.8% on a composite metric combining 5 independent signals - Gemini 2.5 Flash Lite writes 78% like Claude 3 Opus. Costs 185x less - Meta has the strongest provider "house style" (37.5x distinctiveness ratio) - "Satirical…
- BABuilt an Obsidian plugin that rephrases your writing without takin overJun 2026 · rephrasethis.co · ▲5
Writing is hard, and it's tempting to just let AI do the whole thing So I built an Obsidian plugin that keeps AI in its place Highlight a sentence, get some options, pick the one you like Sharpens your writing instead of automating it
- III instructed AI to create tool to clean AI-generated text: undsh.comMay 2026 · undsh.com · ▲5
I can't say "I created a tool" because obviously I only had an idea, then asked Cursor to implement it and 15 minutes later it was ready ;) Often I found I was manually replacing em dashes with hyphens in AI-generated text before I use them in copy, PR descriptions etc. It still feels like a shame to flare the text "you wrote" was not really human made. To automate these removals, here it is: super tiny online page. I made it for myself, but whoever wants, you can use it as well. I am not going to monetize it or promote more than this post.
- CCCallhackernews.com – The missing voice interface for Hacker News2024 · callhackernews.com · ▲9
Hey there HN! I believe the future of AI communication will be more voice and less text. Low-latency realistic voice interactions are finally becoming feasible. I've built a few voice-first apps on Retell AI using Elevenlabs voices. This one uses Claude Haiku for responses and Mixtral to switch between posts and comments. The AI knows about the top 30 posts and their comments on Hacker News right now. After a Google sign-in you can try it free for 10 minutes. I'd love to hear your thoughts!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
