Trivai.app – AI powered trivia questions, with references
Hi HN! As many of you, I've had a lot of fun playing around with LLMs the past few months and I wanted to show you what I've built. I made a trivia website using GPT3 a while back just to have something to play with. My initial interest was to see if I could get structured responses to build a UI around, and if I could get the LLM to refer back to what piece of text it used to create questions and answers with. The initial results were pretty good, but not good enough. Fast forward a few months, GPT 3.5 was released to the public and I was released from my work. I decided to pick this up…
In plain words
Trivai.app is a trivia platform that uses GPT-3.5 to generate multiple-choice questions with source references. Players answer trivia questions while the system cites the specific text passages used to create each question and answer. The platform contains nearly 3,000 generated questions and allows all users to generate additional questions. It's designed for anyone interested in playing AI-generated trivia with transparent sourcing.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! As many of you, I've had a lot of fun playing around with LLMs the past few months and I wanted to show you what I've built. I made a trivia website using GPT3 a while back just to have something to play with. My initial interest was to see if I could get structured responses to build a UI around, and if I could get the LLM to refer back to what piece of text it used to create questions and answers with. The initial results were pretty good, but not good enough. Fast forward a few months, GPT 3.5 was released to the public and I was released from my work. I decided to pick this up again and have been making some changes. - I've generated almost 3000 questions. - I initially only let signed up users generate questions due to cost concerns. Since 3.5 is much cheaper, I've opened up the question generation for everybody. - I built a prompt comparison tool so I could tweak the prompt to get better responses. - I've added some more data to the questions. This includes a more free form explanation to the correct answer (separate from the references), and categories for all questions. - I've been working on a question improvement process. This means I collect issues, generate new variations of the question and let people vote on them. Voting and question improvement is currently only available to signed in users. I have many more ideas I'd like to explore, but I would appreciate your feedback and would be happy to answer any questions about the site or its development. You can access the references by pressing the explanation text when you've answered a question correctly.
Does the same job
all alternatives →- CWChat with multiple LLMs: o1-high-effort, Sonnet 3.5, GPT-4o, and more2025 · polychat.co · ▲62
Hello HN! I was fed up switching between multiple UIs to ask GPT, Claude, etc… the same question and comparing the answers. So I built a way to ask multiple models the same question efficiently by having the LLM compare the responses and only show you new and valuable information from the 2nd model. This way you still get a fast response as normal from the 1st model, but also get any added value provided by the 2nd model. Initially I built my own UI to use this, but stumbled upon Open WebUI (formerly Ollama WebUI) which is fantastic, but is made more for local access to LLMs. So I talked to…
- GFGit for LLMs – A context management interfaceOct 2025 · twigg.ai · ▲106
Hi HN, we’re Jamie and Matti, co-founders of Twigg. During our master’s we continually found the same pain points cropping up when using LLMs. The linear nature of typical LLMs interfaces - like ChatGPT and Claude - made it really easy to get lost without any easy way to visualise or navigate your project. Worst of all, none of them are well suited for long term projects. We found ourselves spending days using the same chat, only for it to eventually break. Transferring context from one chat to another is also cumbersome. We decided to build something more intuitive to the ways humans think.…
- IMI made the slowest, most expensive GPT2024 · ithy.com · ▲74
This is another one of my automate-my-life projects - I'm constantly asking the same question to different AIs since there's always the hope of getting a better answer somewhere else. Maybe ChatGPT's answer is too short, so I ask Perplexity. But I realize that's hallucinated, so I try Gemini. That answer sounds right, but I cross-reference with Claude just to make sure. This doesn't really apply to math/coding (where o1 or Gemini can probably one-shot an excellent response), but more to online search, where information is more fluid and there's no "right" search engine + text…
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, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
