Show HN: I've been using AI to analyze every supplement on the market https://ift.tt/0LxwSrb

Show HN: I've been using AI to analyze every supplement on the market Hey HN! This has been my project for a few years now. I recently brought it back to life after taking a pause to focus on my studies. My goal with this project is to separate fluff from science when shopping for supplements. I am doing this in 3 steps: 1.) I index every supplement on the market (extract each ingredient, normalize by quantity) 2.) I index every research paper on supplementation (rank every claim by effect type and effect size) 3.) I link data between supplements and research papers Earlier last year, I took pause on a project because I've ran into a few issues: Legal: Shady companies are sending C&Ds letters demanding their products are taken down from the website. It is not something I had the mental capacity to respond to while also going through my studies. Not coincidentally, these are usually brands with big marketing budgets and poor ingredients to price ratio. Technical: I started this project when the first LLMs came out. I've built extensive internal evals to understand how LLMs are performing. The hallucinations at the time were simply too frequent to passthrough this data to visitors. However, I recently re-ran my evals with Opus 4.5 and was very impressed. I am running out of scenarios that I can think/find where LLMs are bad at interpreting data. Business: I still haven't figured out how to monetize it or even who the target customer is. Despite these challenges, I decided to restart my journey. My mission is to bring transparency (science and price) to the supplement market. My goal is NOT to increase the use of supplements, but rather to help consumers make informed decisions. Often times, supplementation is not necessary or there are natural ways to supplement (that's my focus this quarter – better education about natural supplementation). Some things that are helping my cause – Bryan Johnson's journey has drawn a lot more attention to healthy supplementation (blueprint). Thanks to Bryan's efforts, I had so many people in recent months reach out to ask about the state of the project – interest I've not had before. I am excited to restart this journey and to share it with HN. Your comments on how to approach this would be massively appreciated. Some key areas of the website: * Example of navigating supplements by ingredient https://ift.tt/KkGc47L * Example of research paper analyzed using AI https://ift.tt/6P5U3sj... * Example of looking for very specific strains or ingredients https://ift.tt/p5WZnv1 * Example of navigating research by health-outcomes https://ift.tt/lXKVSTi... * Example of product listing https://ift.tt/a4X5AJp https://pillser.com/ January 22, 2026 at 07:39PM

Show HN: See the carbon impact of your cloud as you code https://ift.tt/rIiGnod

Show HN: See the carbon impact of your cloud as you code Hey folks, I’m Hassan, one of the co-founders of Infracost ( https://ift.tt/K6W4cqs ). Infracost helps engineers see and reduce the cloud cost of each infrastructure change before they merge their code. The way Infracost works is we gather pricing data from Amazon Web Services, Microsoft Azure and Google Cloud. What we call a ‘Pricing Service’, which now holds around 9 million live price points (!!). Then we map these prices to infrastructure code. Once the mapping is done, it enables us to show the cost impact of a code change before it is merged, directly in GitHub, GitLab etc. Kind of like a checkout-screen for cloud infrastructure. We’ve been building since 2020 (we were part of YC W21 batch), and iterating on the product, building out a team etc. However, back in 2020 one of our users asked if we can also show the carbon impact alongside costs. It has been itching my brain since then. The biggest challenge has always been the carbon data. The mapping of carbon data to infrastructure is time consuming, but it is possible since we’ve done it with cloud costs. But we need the raw carbon data first. The discussions that have happened in the last few years finally led me to a company called Greenpixie in the UK. A few of our existing customers were using them already, so I immediately connected with the founder, John. Greenpixie said they have the data (AHA!!) And their data is verified (ISO-14064 & aligned with the Greenhouse Gas Protocol). As soon as I talked to a few of their customers, I asked my team to see if we can actually finally do this, and build it. My thinking is this: some engineers will care, and some will not (or maybe some will love it and some will hate it!). For those who care, cost and carbon are actually linked; meaning if you reduce the carbon, you usually reduce the cost of the cloud too. It can act as another motivation factor. And now, it is here, and I’d love your feedback. Try it out by going to https://ift.tt/mszeN8R , create an account, set up with the GitHub app or GitLab app, and send a pull request with Terraform changes (you can use our example terraform file). It will then show you the cost impact alongside the carbon impact, and how you can optimize it. I’d especially love to hear your feedback on if you think carbon is a big driver for engineers within your teams, or if carbon is a big driver for your company (i.e. is there anything top-down about carbon). AMA - I’ll be monitoring the thread :) Thanks https://ift.tt/mszeN8R January 21, 2026 at 08:34PM

Show HN: Xv6OS – A modified MIT xv6 with GUI https://ift.tt/gfzemd7

Show HN: Xv6OS – A modified MIT xv6 with GUI I've been working on a hobby project to transform the traditional xv6 teaching OS into a graphical environment. Key Technical Features: GUI Subsystem: I implemented a kernel-level window manager and drawing primitives. Mouse Support: Integrated a PS/2 mouse driver for navigation. Custom Toolchain: I used Python scripts (Pillow) and Go to convert PNG assets and TTF fonts into C arrays for the kernel. Userland: Includes a terminal, file explorer, text editor, and a Floppy Bird game. The project is built for i386 using a monolithic kernel design. You can find the full source code and build instructions here: https://ift.tt/h9KnvAd January 20, 2026 at 10:46PM

Show HN: Trinity – a native macOS Neovim app with Finder-style projects https://ift.tt/iQBaw4P

Show HN: Trinity – a native macOS Neovim app with Finder-style projects Hi HN, I built Trinity, a native macOS app that wraps Neovim with a project-centric UI. The goal was to keep Neovim itself untouched, but provide a more Mac-native workflow: – Finder-style project browser – Multiple projects/windows – Markdown preview, image/pdf viewer – Native menus, shortcuts, and windowing – Minimal UI, no GPU effects or terminal emulation It’s distributed directly (signed + notarized PKG) and uses Sparkle for incremental updates. This started as a personal tool after bouncing between terminal Neovim and heavier editors. Curious to hear feedback from other Neovim users, especially on what feels right or wrong in a GUI wrapper. Site: https://ift.tt/IkKNeiP Direct download: https://ift.tt/QVaWt3K... https://ift.tt/IkKNeiP January 20, 2026 at 11:14PM

Show HN: Homunculus – A self-rewriting Claude Code plugin https://ift.tt/uz29ikW

Show HN: Homunculus – A self-rewriting Claude Code plugin Homunculus is a Claude Code plugin that watches how you work and writes new capabilities into itself. If you keep doing something repeatedly—checking docs before API calls, running the same debug flow, formatting PRs a certain way—it notices and offers to automate it. Accept, and it writes a new markdown file into its own structure. The plugin literally changes based on what you do. It can create: Commands (explicit shortcuts) Skills (context-triggered behaviors) Subagents (specialists for specific problem domains) Hooks (event-driven, like "run tests when these files change") What actually works (v0.1): Commands are deterministic. Skills are probabilistic—they fire when Claude decides they're relevant, maybe 50-80% of the time. It's an experiment in making LLM tooling adaptive rather than static. State stored in .claude/homunculus/. Each project gets its own instance. https://ift.tt/mNBMOv8 January 19, 2026 at 11:23PM

Show HN: Subth.ink – write something and see how many others wrote the same https://ift.tt/e87bJPw

Show HN: Subth.ink – write something and see how many others wrote the same Hey HN, this is a small Haskell learning project that I wanted to share. It's just a website where you can see how many people write the exact same text as you (thought it was a fun idea). It's built using Scotty, SQLite, Redis and Caddy. Currently it's running in a small DigitalOcean droplet (1 Gb RAM). Using Haskell for web development (specifically with Scotty) was slightly easier than I thought, but still a relatively hard task compared to other languages. One of my main friction points was Haskell's multiple string-like types: String, Text (& lazy), ByteString (& lazy), and each library choosing to consume a different one amongst these. There is also a soft requirement to learn monad transformers (e.g. to understand what liftIO is doing) which made the initial development more difficult. https://subth.ink/ January 20, 2026 at 12:04AM

Show HN: Xenia – A monospaced font built with a custom Python engine https://ift.tt/wyX69Pl

Show HN: Xenia – A monospaced font built with a custom Python engine I'm an engineer who spent the last year fixing everything I hated about monofonts (especially that double-story 'a'). I built a custom Python-based procedural engine to generate the weights because I wanted more logical control over the geometry. It currently has 700+ glyphs and deep math support. Regular weight is free for the community. I'm releasing more weights based on interest. https://ift.tt/y8iUAxb January 18, 2026 at 04:09PM