{"slug": "offline-dsa-interviewer-the-llm-talks-the-code-decides", "title": "Offline DSA Interviewer: The LLM Talks, the Code Decides", "summary": "A developer built an offline, local-first mock DSA interviewer that runs an open-weights LLM entirely on the user's machine, walking candidates through clarifying questions, approach, graduated hints, hidden test runs, complexity analysis, and edge cases. The tool was created for a friend preparing for coding interviews who lacked practice partners, and keeps all code, voice, and mistakes on the laptop with no per-session cost or third-party API calls.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nAn offline mock DSA interviewer. You pick a problem, think out loud while you code in the browser, and it behaves like a real interviewer: it asks for your approach before you code, gives graduated hints when you're stuck, runs your solution against hidden tests, asks for complexity, then throws edge cases at you.\n\nI built it for ****, who **[one honest sentence: what they're preparing for and what's been hard for them, e.g. nobody to practice with, can't afford paid mock interviews, or doesn't want their voice and half-formed code sent to someone's server]**. It gives them unlimited practice, free, with nothing leaving their laptop.\n\nIt's local-first, so the demo is a screen recording of a full interview: clarify, approach, a failing run, a hint, a passing run, complexity, edge cases, report.\n\nA practice interview exposes your half-formed thinking, your mistakes and your voice. With open weights running locally, all of that stays on the machine. It works without internet, costs nothing per session, and anyone can swap the model or edit the interviewer's rules. A closed API would mean per-call costs, rate limits, and sending someone's struggle to a third party. For a friend practicing under pressure, that trade matters.", "url": "https://wpnews.pro/news/offline-dsa-interviewer-the-llm-talks-the-code-decides", "canonical_source": "https://dev.to/abhinav_garg_05/offline-dsa-interviewer-the-llm-talks-the-code-decides-4i48", "published_at": "2026-10-05 04:36:11+00:00", "updated_at": "2026-10-05 04:42:46.850041+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "developer-tools", "ai-agents"], "entities": [], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/offline-dsa-interviewer-the-llm-talks-the-code-decides", "markdown": "https://wpnews.pro/news/offline-dsa-interviewer-the-llm-talks-the-code-decides.md", "text": "https://wpnews.pro/news/offline-dsa-interviewer-the-llm-talks-the-code-decides.txt", "jsonld": "https://wpnews.pro/news/offline-dsa-interviewer-the-llm-talks-the-code-decides.jsonld"}}