2025年10月4日 の Show HN

Hi HN — I’m learning Rust and decided to build a universal CLI for running code in many languages. The tool, Run, aims to be a single, minimal dependency utility for: running one-off snippets (from CLI flags), running files, reading and executing piped stdin, and providing language-specific REPLs that you can switch between interactively. I designed it to support both interpreted languages (Python, JS, Ruby, etc.) and compiled languages (Rust, Go, C/C++). It detects languages from flags or file extensions, can compile temporary files for compiled languages, and exposes a unified REPL experience with commands like :help, :lang, and :quit. Install: cargo install run-kit (or use the platform downloads on GitHub). Source & releases: https://github.com/Esubaalew/run I used Rust while following the official learning resources and used AI to speed up development, so I expect there are bugs and rough edges. I’d love feedback on: usability and UX of the REPL, edge cases for piping input to language runtimes, security considerations (sandboxing/resource limits), packaging and cross-platform distribution. Thanks — I’ll try to answer questions and share design notes.

Hey parents! If your child has lost a tooth, pair that money offer with a nice certificate from the tooth fairy itself!

Terminal tool to search arXiv papers and render them as beautiful HTML for humans and LLMs

I built BetterSelf to solve a problem I kept running into: most of what we learn, we forget. Books, podcasts, and notes — valuable insights disappear in days.

BetterSelf keeps your best lessons and ideas alive, reminding you over time so they actually stick. I use it every day, and it’s already helped me retain things I would have forgotten.

I’m 19 and built this in about a month while experimenting with personal productivity tools.

I’d love feedback from the HN community — anything you suggest will go straight into the app.

Thoughts?

If you want to play around with this, one of the best ways is to drop the contents of the website, the GitHub README, and the entire overview.md into an AI chat. Then you can co-create with it. Gemini Pro 2.5 can handle the entire doc in one prompt, and its ability to co-create ideas is absolutely incredible. I've been using it mostly through the AI Studio interface. Much of the overview is as much my work as it is a synthesis of my collaboration with Gemini Pro 2.5, ChatGPT-4o, and some early contributions from GPT-4 about a year ago.

Before LLMs, I was building out pamphlet-style pages on a website (that are up at whomanatee.org, which is the base wrapper implementation of the framework), and I was planning to use them as talking points. I was anticipating that much of the deep thinking would have to happen in slow, public discourse. With LLMs, I've been able to stress-test these ideas from every possible angle, using any past event or theory to see if the framework could withstand scrutiny.

It's a fascinating new process. At one point, a model argued that Adam Smith would have rejected this idea as fantasy. So, I worked with it to develop an economic plan that "synthetic Adam" praised it to the moon. It's incredible that we now have the ability to get synthesized thoughts from almost any perspective. You could ask it, "What would Barack Obama think of this plan? And using the framework, what would be your response to any hesitations he may have?" And BOOM, you get incredible analysis and synthesis and feedback.

The core documentation should answer most mechanical questions. And if you feed the docs into an AI chat, you can ask it any question you may have, or to simply ask it to explain something in different ways.

Also, would y'all want me to pre-prime a chat in Google AI Studio with the full context of the plan and some basic direction for discourse? I can share a link to a ready-to-go environment.

Porting of the suckless surf browser for Wayland

A proxy for your main email

I made my own system to create & maintain custom guitar tab sheets. It uses Cursor's agent loop to automate what I used to do manually - scour Ultimate Guitar for tabs of every part of the song and piece it together.

You can ask for tabs in the structure you like by amending the instructions in AGENTS.md.

Hope someone finds this useful!

The RL ecosystem is maturing— verifiers are standardizing how we build and share environments. However, as it grows, we need observability tooling that actually understands RL primitives.

Running RL experiments without visibility into rollout quality, reward distributions, or failure modes is a waste of time.

Monitor provides live tracking, per-example inspection, and programmatic access—see what's happening during runs and debug what went wrong afterward.

v1.1.0 adds ~20–30% faster responses and better tool calling. Curious how people might wire this into their workflows?