nowfound

AI · August 12, 2026

I took the calculator away from 50 LLMs and graded the arithmetic

Contribute to DmitriGoloubentsev/LLM-Tests development by creating an account on GitHub.

Does the same job

all alternatives →
  • IM
    I made a web game that makes practicing basic arithmetic fun2024 · worchle.com · ▲161

    Hey, maker here. After launching a daily word search game, I randomly thought of this math game while driving. Finally got around to making it and I think it turned out pretty cool. It’s a math search game that’s meant to help you practice your quick addition, subtraction, multiplication, and division skills. I’m hoping it’ll help people (even those like me who aren’t big on math) learn and increase their speeds. (There are also some settings you can enable to make the game harder) If you try it out, please let me know if you found it fun, if you have anything you’d like me to add, or if you…

  • IQ
    I quit coding years ago. AI brought me backJan 2026 · calquio.com · ▲314

    Quick background: I used to code. Studied it in school, wrote some projects, but eventually convinced myself I wasn't cut out for it. Too slow, too many bugs, imposter syndrome — the usual story. So I pivoted, ended up as an investment associate at an early-stage angel fund, and haven't written real code in years. Fast forward to now. I'm a Buffett nerd — big believer in compound interest as a mental model for life. I run compound interest calculations constantly. Not because I need to, but because watching numbers grow over 30-40 years keeps me patient when markets get wild. It's basically…

  • AD
    All desktop software calculators are wrong, so I had to build my own2022 · ▲286

    A new calculator software cannot really bring attention (https://chachatelier.fr/chalk/) However, I wrote a full article explaining why I had to build something "new" that does not behave like usual desktop calculator softwares : TL;DR All "small" calculator softwares I know share the same design flaws. And the GUI is not the only stumbling block in their poor efficiency. Handling correctly numerical approximations - expected or not - is crucial to trust the results. It is usually not done in lightweight tools. It should. So I prove that if I could do it, OS manufacturers…

  • QuickCompare by TrismikApr 2026 · trismik.com · ▲231

    Compare LLMs on your data, measure, and pick the best.

  • IM
    I made an interactive math crossword puzzle with infinite levels2024 · scientific.place · ▲165

    Hey there! I'm the brains behind the math crossword game on my site. This game is all about making math a little more fun – users just drag and drop numbers to fill in the blanks and move on to the next level if they get it right. Let me know if face any issues or have any suggestions! :)

  • IM
    I'm 17 and I created a Forth interpreter for the TI-84+ calculator2018 · ▲56

    https://github.com/siraben/ti84-forth Hi HN! For the past year I've been getting into programming in Z80 assembly (especially for the TI-84+). More recently I've been learning about the Forth programming language and after a lot of searching online (in vain) for a Forth interpreter for the TI-84, I decided to write one myself. It's been fun demoing this to others, because it's a very unexpected use of a calculator. It's my largest project to date, and I'm interested to know what the HN community thinks, please feel free to critique my code! -- Ben

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

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • 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

  • Turn website visitors into qualified pipeline

    AI · 19d ago · clarasdr.ai

  • Kane CLI446

    Natural language browser & mobile app tests from terminal

    AI · 24d ago · testmuai.com

Launched alongside, August 2026

the whole month →
  • TL

    Life & fun · 10d ago · louisabraham.github.io

  • Hey Noah641

    A proactive AI executive assistant for founders

    AI · Aug 2026 · heynoah.io

  • Let agents source clips from terabytes of your local video

    Work · 18d ago · clipto.com

  • 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

  • AdAnt AI608

    Claude for viral, high-converting social ads

    AI · Aug 2026 · adant.ai

  • 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