Hacker News: aadyachinubhai

New comment by aadyachinubhai in "Tracing np.add, all the way down"

aadyachinubhai — Wed, 09 Sep 2026 07:23:30 +0000

The `.c.src` files with the @arch@ like dispatching logic is specific to numpy. Also, they are currently making efforst to shift to C++ templates using Google's Highway project. I worked on porting `np.negative` to it!

New comment by aadyachinubhai in "The Navier–Stokes Millennium Prize Problem"

aadyachinubhai — Wed, 09 Sep 2026 06:37:55 +0000

LLMs can't contribute good code to some of the good OSS math libraries, How is it even solving these problems?

New comment by aadyachinubhai in "Show HN: n8n like workflows for AI agents that control a real VM"

aadyachinubhai — Mon, 11 May 2026 23:44:06 +0000

Each node in the graph is a plain English instruction. An AI agent executes them in order inside a Docker container with a full browser and desktop. Because each node is independent, the agent stays on task, it doesn't drift or hallucinate its way through a free-form prompt.

No programming required to build workflows. If you can describe a step, you can add a node.

I personally use it for:

- Applying to jobs automatically using my saved credentials, exactly the way I would do it manually

- Scraping websites and running data analysis on the results in the same workflow

- Checking my university LMS on a schedule for pending assignments

A few technical details:

- Nodes: Navigate, Do, Read, Fill, Check, Code, ForEach, Bootstrap

- Any LLM via LiteLLM: Gemini, GPT-4o, Claude, Ollama, OpenRouter

- Watch it work over noVNC, pause and take control, hand back anytime

- Chrome sessions persist across restarts via a named Docker volume

- Webhook + cron triggers, secrets vault, human-in-the-loop confirmation per step

GitHub: github.com/aadya940/orbit-ui

Docs: orbit-cua.com

Show HN: n8n like workflows for AI agents that control a real VM

aadyachinubhai — Mon, 11 May 2026 20:24:10 +0000

Article URL: https://github.com/aadya940/orbit-ui

Comments URL: https://news.ycombinator.com/item?id=48100204

Points: 6

# Comments: 1

New comment by aadyachinubhai in "Show HN: Structured Python control over AI computer use agents"

aadyachinubhai — Thu, 02 Apr 2026 04:11:02 +0000

Fair, mature frameworks do a lot more. Orbit isn't trying to out-feature them. It's a thinner abstraction specifically for computer-use, where the bottleneck isn't orchestration complexity, it's controllability at the step level. Different problem.

New comment by aadyachinubhai in "Show HN: Structured Python control over AI computer use agents"

aadyachinubhai — Thu, 02 Apr 2026 02:14:11 +0000

Most agents are prompt + a bunch of tool calls. Writing everything in one prompt is like writing your entire app in one function. It works until it doesn't, and when it doesn't, you have no idea where it broke. Orbit gives you steps and python control flow instead of prompts, so failures are local, models are swappable, and budgets are per-action. This makes it debuggable.

For example, Your `Read` step failed after 3 LLM calls on step 4 of 7. With a monolithic prompt, that's just... it hung.

Show HN: Structured Python control over AI computer use agents

aadyachinubhai — Wed, 01 Apr 2026 23:57:17 +0000

Most CUA frameworks are either a black box or raw tool calls with no structure. Orbit sits in between, natural language controls the screen, Orbit lets Python control the flow. Each step has its own model, budget, and typed output, but shares context across the session. Mix cheap and expensive models per step, extract structured data from any screen into Pydantic models, and steer the agent mid-task when it struggles. Built on the OS accessibility tree, not screenshots.

https://github.com/aadya940/orbit

Comments URL: https://news.ycombinator.com/item?id=47608250

Points: 1

# Comments: 4

New comment by aadyachinubhai in "ChainoPy: A Python Library for Discrete Time Markov Chains"

aadyachinubhai — Mon, 07 Jul 2025 07:08:02 +0000

Why ChainoPy? Covers most of the fundamental agorithms for Markov Chain Analysis Memory efficient Model saving Faster than other libraries (eg: 5x Faster than PyDTMC) First Package to contain functions to build equivalent Markov Chain Neural Networks from Markov Chains. Contains Markov Switching Models for Univariate Time Series Analysis

ChainoPy: A Python Library for Discrete Time Markov Chains

aadyachinubhai — Mon, 07 Jul 2025 07:08:02 +0000

Article URL: https://github.com/aadya940/chainopy

Comments URL: https://news.ycombinator.com/item?id=44487500

Points: 1

# Comments: 1

Show HN: Autoresume – OpenSource, Resume Builder and TeX Editor with AI Features

aadyachinubhai — Sun, 06 Jul 2025 17:27:02 +0000

A new opportunity pops up, but your resume is hopelessly out of date. You copy content from LinkedIn, dig up old projects from GitHub, and try to remember what you actually accomplished at your last job. Then comes the formatting Word, Google Docs, endless font tweaks, and still, it never looks quite right. And if you want to tailor your resume for a specific job? That’s another evening gone.

I built autoResume because I was tired of this cycle. I wanted a tool that made resume building as easy as pasting a link or dropping in a job description. With autoResume, you can:

Paste your professional links (GitHub, personal site, LinkedIn) and instantly pull in your achievements.

Edit manually when you want full control, with a clean, code-like editor.

Let AI help polish, update, and even tailor your resume to specific roles, just paste the job description.