Harfi
It does exactly what you said. Not what you meant.
What it does
Forty trials, each a spec an AI's answer has to hit exactly — three bullets, fifty words, valid JSON, no letter O. You never write the answer, only the instruction. A parser scores it, never an opinion. Fewest strokes wins.
A game where you write the instruction, not the answer. Forty trials, each a spec an AI's output must hit exactly — checked by a parser, never by an opinion.
Not what you meant. Forty trials, each one a spec the machine's answer has to hit — exact bullet counts, hard word caps, forbidden letters. Get it there in as few strokes as you can. Explain a black hole in 60 words or fewer — without ever using the words gravity, light, star, space, or massive. Describe a black hole for a curious adult. Under 60 words. Banned words: gravity, light, star, space, massive. Check every word before you answer. Every trial hands you a set of rules the answer must satisfy. Exactly three bullets. Sixty words, hard cap. Five words you may not use. You never write the answer. You write the instruction that makes the machine produce it — in 120 words or fewer.…from harfi.games
Does the same job
all alternatives →
- CYCan you meld minds with AI and guess the same word?2025 · convergegame.com · ▲11
I built a daily word association puzzle where you engage in a quiet, collaborative mind meld with AI. I'd love to have folks try it out and tell me what they think! Here's how it works: 1. Enter your first word to reveal the AI's word of the day. 2. Don't think too hard about it. It's just a starting point. 3. Both of you think of a word that connects the two. 4. To win, you need to say the same word. 5. You have 8 guesses to converge. 6. Need a hint? The AI will drop a riddle in your final two guesses. HOW DOES IT WORK? After the user_word + ai_word are submitted, I trigger two separate LLM…
- IBI built a Wikipedia based AI deduction gameApr 2026 · sleuththetruth.com · ▲9
I haven't seen anything like this so I decided to build it in a weekend. How it works: You see a bunch of things pulled from Wikipedia displayed on cards. You ask yes or no questions to figure out which card is the secret article. The AI model has access to the image and wiki text and it's own knowledge to answer your question. Happy to have my credits burned for the day but I'll probably have to make this paid at some point so enjoy. I found it's not easy to get cheap+fast+good responses but the tech is getting there. Most of the prompts are running through Groq infra or hitting a cache…
- APAI Poetry Contest2023 · acontestofwords.com · ▲8
Hi HN! Me and my buddy made this in a weekend as an experiment in 1. building something quickly and putting it out there and 2. using AI in an interesting way; in this case a poetry judge. Our “judge” isn’t perfect, but the hope is that at least it’s a relatively fair system that everyone can be sure evaluates their work. Anyway, we wanted to see what the lovely people of HN think of it. Some background on the idea; I like poetry and thought it would be cool if there was a big competition with a large financial incentive that scales with the number of participants. Using AI as a judge allows…
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
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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