I built an AI tool to practice technical interviews with
Hey HN, Check out our technical paper here: https://arxiv.org/abs/2501.15627 and the video demo: https://www.youtube.com/watch?v=Op8hyLW7Z84 I’ve been obsessed with the art of the interview since I was in college. In my career I interviewed over 100 people and was interviewed from tech companies from startups to big tech and hedge funds. I built Neuraprep because I noticed something missing — while software engineers have leetcode.com and finance folks have quantquestions.com, other engineering domains (like ML, data science, MLOps) don’t have a go-to…
In plain words
Neuraprep is a platform for practicing technical interviews in specialized engineering fields like machine learning, data science, and MLOps. It provides over 400 real interview questions with detailed answers compiled from academic sources and online communities. The tool is designed for engineers in these domains who lack a unified preparation resource comparable to platforms available for software engineers or finance professionals.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, Check out our technical paper here: https://arxiv.org/abs/2501.15627 and the video demo: https://www.youtube.com/watch?v=Op8hyLW7Z84 I’ve been obsessed with the art of the interview since I was in college. In my career I interviewed over 100 people and was interviewed from tech companies from startups to big tech and hedge funds. I built Neuraprep because I noticed something missing — while software engineers have leetcode.com and finance folks have quantquestions.com, other engineering domains (like ML, data science, MLOps) don’t have a go-to platform to prep for interviews. Sure, there’s Kaggle and Coursera, but nothing unified. So I spent a summer collecting 400+ real interview questions and built detailed answers for each. I drew from academic sources, online communities, and LLMs to refine the content. Then I used this dataset to build an AI that mimics how a human interviewer evaluates responses. Here’s how it works: • The reasoning engine extracts core ideas from the user’s answer. • It compares them to the expected ideas from the database. • If something is missing, the conversation continues — just like a real technical interviewer would do. With recent voice and reasoning model advancements (thanks Sesame, O3), it now runs on-demand phone interviews that feel surprisingly real.
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 · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
