惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
B
Blog RSS Feed
量子位
aimingoo的专栏
aimingoo的专栏
V
Visual Studio Blog
Y
Y Combinator Blog
Vercel News
Vercel News
云风的 BLOG
云风的 BLOG
宝玉的分享
宝玉的分享
Engineering at Meta
Engineering at Meta
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
GbyAI
GbyAI
人人都是产品经理
人人都是产品经理
博客园 - 叶小钗
Stack Overflow Blog
Stack Overflow Blog
大猫的无限游戏
大猫的无限游戏
Microsoft Security Blog
Microsoft Security Blog
B
Blog
Last Week in AI
Last Week in AI
有赞技术团队
有赞技术团队
博客园 - 聂微东
腾讯CDC
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
J
Java Code Geeks

HN's home page

Rainbow Query Language | Hacker News Exec into Node via Kubectl An AI native hedge fund The Seven-Action Documentation Model | Hacker News Package Manager for Kubectl Plugins Tongan Castaways | Hacker News Tech overlords plan for conscious AI to conquer the cosmos. What could go wrong? Data Breach Disclosure Lag Is Getting Worse How LLMs Work | Hacker News I Dropped PRDs for Shape Up Go Experiments Explained | Hacker News FCA's Palantir deal could expose UK financial data to Trump's US, critics fear WebXR BCI for Neural-Adaptive Avatar Control in Mixed Reality The first murder conviction via DNA analysis Tom Interviews Theo de Raadt of the OpenBSD Project (2019) [video] Show HN: Replace shell commands with bun shell typescript scripts Quay.io Is Down | Hacker News AI driven analysis of brokerage account fees in the UK Bill Gates Spent Years Crafting His Image. Now It's Cracking Using LLMs to secure source code Wi-Fi 8 in the Lab [video] The household battery revolution that could change energy bills and the world Is Python Becoming Pinyin? | Hacker News Livia – Executive Assistant | Hacker News FindMyPipe – Query Apple Find My from Linux for AI Agents Show HN: Agent skill for creating product launch videos with Remotion RecruitMyself – AI job search copilot for resumes and applications AI coding agents and the erosion of system understanding The 'Resting' Generation and South Korea's Youth Recession AMD Computex 2026: 10 Years of AM4, AM5 Support Through 2029
Companies automated hiring, so I automated the job hunt
Liebmann5 · 2026-06-23 · via HN's home page

Hi,

My name is Nick, and I'm a hobbyist programmer! Several years ago after applying to hundreds of jobs began to recognize that companies had been using tools to help make the hiring process more efficient from their end and realized candidates lacked really any tools similar so decided to make one! I figured that, like me, other job seekers were stuck manually applying to online jobs by repetitively filling out the same information over and over again with really no good tools to do it for them.

So, I built AA (aka AutoApply)... and it's almost finished!

AA is a 1000% free, fully autonomous, open-source agent that discovers, vets, and applies to jobs for you. Here is how the program is broken down and works

Discovery: It reads and extracts information from search engines, job boards, and company career pages to find available jobs. Vetting: It utilizes local NLP (SpaCy) to ensure a "Two-Way Fit" meaning is this a job the candidate finds fit and does the candidate align with what the company is looking for. It checks if attributes like salary, location/commuting distance, and required skills match your profile information! Apply: It can upload resumes, cover letters, CV's, handles multi-page forms, logins, and even uses a local offline AI (GPT4All) to write personalized answers to open-ended questions such as "Tell us about a challenge you over came at specifically 6 years old and why you didn't graduate from Harvard".

I designed this with a few core philosophies in mind that I'm really proud of

-Worst-Case First: It designed to be run on a 2GB RAM library computer with zero admin rights. -Flash Drive Capability: I don't own nor can afford a laptop so can download AA onto a USB stick(flash drive) and run it completely portably. -Undetectable: It has a built-in evasion framework. It spoofs lots of browser information and human behavior (Bezier-curved mouse movements & parabolic typing delays). -Accommodate Everyone: I hate when things don't work so throughout the entire build I always wanted to accommodate to every and all users NOT them accommodate to or for me! -Everything Customizable: I mentioned it can work autonomously but can be run other ways such as with user supervision "Human-in-the-Loop (HITL)" which means you can set checkpoints for where you wish AA to stop to input specifically personal information if you'd like. -The Research Platform: Nearly all hiring/job market data is owned and released by employers. AA has an opt-in, strictly anonymized (Zero-PII) research module to perhaps offer a new perspective on that data. It recognizes and reports things like ghosting rates, biases, various forms of discrimination, unethical business practices, and plenty more. My goal was and is to build a candidate-side dataset on the hiring market that is academically publishable.

I'm almost done with the project so if you're job hunting and think you could/would use this please leave a note or comment! If you are a developer/engineer, I'd love your feedback on anything from the architecture (strict Hexagonal Ports & Adapters design) to the safety and security production level code for a project like this and even just professional insight would be amazing! If you are a Mathematician, my Math Subsystem utilizes spatial geometry to break down webpages for the autonomous feature and I'd like all my Math to be deterministic, pure mathematical algorithms for the research and "open-ended questions" code and finally my Research Signal Detectors use things like Wilson's score interval, Fisher's exact test, Kendall's Tau, etc.! If you are a Researcher or in Academics, I truly have no idea what I'm doing nor if anything is correct so any review or help or insight would be phenomenal!