experiment - Moozonian Search

motraapp.com• Jul 16, 2026• 1 min read

Show HN: Effort Lab – Same running pace, different heart rate zonesHi HN,If you are into fitness, I hope you’ll find this interesting.I’ve been building a fitness app around a question that ordinary activity summaries and fitness apps don’t answer particularly well:“How hard did this session ask my body to work?”Imagine two friends running a 5K together at 5:30/km. Same route, same distance and the same 27:30 finish time.In the synthetic example linked here, they even have the same average heart rate. Most fitness apps would treat those runs as virtually identical. However, relative to their individual profiles, Alex is working at 69% of his current maximum heart rate—Zone 2—while Sam is at 82%, which places him in Zone 4.I built a quick interactive page based on that thought experiment. Move the pace control between 3:00 and 7:00/km and watch the same external output place each runner in different personal heart-rate zones.I’m not suggesting that training raises maximum heart rate, (that is a far more nuanced debate). What is clear is that each perso

developer.puter.com• Jul 15, 2026• 1 min read

Show HN: Firefox in WebAssemblyThis is the entire Firefox browser rendering to a element. Gecko, all UI components, and the Spidermonkey JS engine are all compiled and running in WebAssembly.Here are a few things you might find interesting:- This is fully end to end encrypted! We use the WISP protocol for TCP-over-websockets.- There is a novel WASM->JS JIT for experimental site speedup- This port cost over 25k in opus/fable tokens for debugging and JIT researchThis was just a fun experiment to push the boundaries of WebAssembly. For a more usable "browser in browser" experience, we also built https://github.com/HeyPuter/browser.js that eats a bit less RAM.

withmurph.ai• Jul 15, 2026• 1 min read

Show HN: OpenClaw for Your HealthHey HN! I built https://withmurph.ai, an open-source personal health assistant to help you build healthy habits that actually stick. Everyone has something they want to improve, but it's way too hard to change your behavior.I've been using Murph myself for weeks, I've started a few sleep improvement experiments with Murph that've improved my deep sleep already, and run some challenges over group-text with friends.Murph has three key features 1) Talk to Murph on iMessage, Telegram, and Email and connect labs/wearable data 2) Run health experiments with proactive check-ins and discover what protocols improve your health. 3) Run health challenges with friends inside group-textsSome other things our users are doing: - help manage chronic pain and track what causes symptom flareup over iMessage - watch calories and protein intake every day by sending voice memos/photos of meals - find workout insights in mountains of lab and wearable data - build a physical therapy habit to improve lower ba

github.com• Jul 13, 2026• 1 min read

Show HN: Clay Seal Identity – Agents need accountabilityAI agents are starting to get real access like GitHub tokens, cloud credentials, customer data, deploy permissions. Not coincidentally, the rate of major cybersecurity incidents is rising rapidly. See for yourself: https://epoch.ai/data/cve?view=graph https://genai.owasp.org/resource/state-of-agentic-ai-securit... My friend and I, both AI researchers, are working on fixing this through an open-source project we've just started called Clay Seal.We've started with a simple version of Identity: an open-source way to issue short-lived, verifiable identities to AI agents. We're working on several experimental components, including runtime query-based capability scoping for agents, followed by AML-inspired suspicious behavior detection, to replace the antiquated system of static sandboxes most AI tools run on. These tools will enable you to protect yourself from many classes of attacks and are, based on our testing, performing quite well on public benchmarks (which we'll publish soon when we

github.com• Jul 13, 2026• 1 min read

Show HN: Containerized AI development with cross-compatibilityI need to study different harnesses CLI, and to find a way to switch from one provider to another.I built a template repository to govern your AI chats with more grip than usual. It leverages PI.dev coding agent and an aggressive isolation done with Docker + VS CodeSo far works on Linux and MacOS, and should also works on WSL2.The project uses a container to run your preferred AI harnesses CLI. The container is optional, but protect your disk from bad things (I noticed rm -rf is always the preferred removal command of Deepseek :) a bit scary)I am slowly extending it, aiming at- reduce token usage - ability to install extra skill via pi.dev - experimenting with variants (like AWS AI-SDLC v1).Please feel free to comment and give me hints.

news.ycombinator.com• Jul 13, 2026• 1 min read

I built an artificial lifeform descended from youHi HN,Everyone is waiting for consciousness to emerge in AI, right?Then I thought, why wait? Why not transplant ourselves instead?I architected SelfEidolon as an alpha experiment in self-evolving artificial lifeforms.It is not an AI assistant.It is an artificial lifeform descended from you.The alpha is invite-code only and limited to the first 1,000 users.Only 10 Invite Codes have been publicly released by SelfEidolon.They are available in Discord.https://discord.gg/P646MFAxbbAfter the first 10 people activate their Eidolons, access will require an invitation from one of them.

costbase.co• Jul 13, 2026• 1 min read

Show HN: Costbase – See what each of your AI apps costs, without a proxyLive demo, no signup: https://costbase.co/demoHi there, over the past 1-2 years I've built and experimented with many AI apps. Some are in production, some died in the experimental stage.The ones in production currently costs me ~$500 a month to run – using a variety of models from OpenAI's Whisper to Anthropic LLM.Because it's important for me to track the Cost of Goods Sold of each individual app, the strategy I've used so far is to use a different credit card for my few apps. However, that obviously does not work the more apps I build.This is why I built Costbase – a simple app that just requires that I paste in an admin key with no code change (and no proxy sitting between my app and the AI provider) – and show me the cost of my AI bill broken down by apps and not API keys.I intentionally kept this product as simple as possible – something I would actually like to use. I know there are observability tools like Helicone that are much more capable. But to be honest I didn't even try

github.com• Jul 13, 2026• 1 min read

Show HN: Aco – Appium Command-Line OperatorHi, I created a CLI tool called aco to help spin up Appium session rapidly.I'm a programmer who've been working on mobile app automation for end-to-end testing for years. Appium is the industory standard in this area. It's basically a WebDriver protocol server spetiallized for non-browser apps like iOS/Android. The beauty of Appium is its clean separation of the responsibility by the client/server architecture. So consumers select any language binding they like when use it. It means you typically need to care of server and client at the same time, and this is the pain.As a mobile automation engineer, I often need to run a small experiment to make sure of the behavior of AUT(application under test) or Appium itself: how long does it take to fetch page source from a complex screen, how much ScrollView moves to a specific swipe amount, what's hapenning behined the sceen when some letters are dropped from text sent, etc. When it comes, I usually write a small script tp send commands to ser

bing.com• Jul 13, 2026• 1 min read

Mizuno’s running shoe lineup is more exciting than ever. Here are the best pairs we tested for 2026Mizuno is famous for its workhorse trainers, but the brand has an experimental side, too: These are the best pairs to try.

news.ycombinator.com• Jul 12, 2026• 1 min read

Ask HN: Would filesystem bookmarks be useful in your shell workflow?I’m experimenting with a small shell utility for filesystem bookmarks, and I’d like to understand whether this is a problem other people have.The idea is to define persistent or temporary bookmarks for directories:``` bm add work ~/Work bm temp build /tmp/build ```and then use them directly in paths:``` cd @work ls @work/project ```The utility would also support renaming bookmarks, promoting temporary bookmarks to persistent ones, demoting them, and clearing temporary bookmarks.I’m not sharing the implementation yet. At this stage, I’m mainly interested in how other people handle this today:* Do you use aliases, environment variables, shell functions, z, autojump, or something else? * Would explicit names such as @work be useful, or would they feel redundant? * Would temporary bookmarks be useful in real workflows? * What would this need to offer to be worth using instead of existing directory-jumping tools?

github.com• Jul 11, 2026• 1 min read

Show HN: Clx – Compile Lua to Native Executables Through C++20Hi HN,clx is an ahead-of-time compiler for standard Lua that generates C++20 and produces standalone native executables through GCC, Clang or MSVC.The project started as an experiment to see whether modern C++ could be used as a portable compiler backend instead of LLVM or direct machine code generation. The generated code is then compiled and optimized by the host toolchain.The latest release replaces the previous NaN-tagged value representation with a new shadow-types implementation, adds full int64 support, improves native arithmetic code generation and adds ARM64 macOS coroutine support.Performance is typically much faster than the Lua interpreter and can outperform LuaJIT on some computation-heavy workloads while remaining fully ahead-of-time compiled.The repository also contains graphical examples written in Lua, including a Pong game and a Mandelbrot explorer using a Sokol binary module (using the clx C++ API)I'd be very interested in feedback on clx :)

github.com• Jul 10, 2026• 1 min read

FreedomLang – native x86-64 HTTP with no libc / no CRTI'm sharing a small milestone today - a tiny HTTP server written in FreedomLang (freelang), which is a new, experimental, AOT-compiled language I've been working on.The demo (httpd.flx) compiles down to native x86-64, and the resulting server runs with no C runtime/libc dependency (it uses direct syscalls on macOS and Linux, and Winsock plus Kernel32/WS2_32 on Windows).If you want to poke around you can clone the repo, build it (the compiler is just a Node.js script, very inspectable), and test it with a simple curl localhost/health or curl localhost/ . You can also inspect the native machine code with tools like otool -L on macOS to verify the lack of Mach-O dynamic-library dependencies.The reason I chose a tiny HTTP server was it shows an actual socket lifecycle (accept/read/respond/close), but it doesn't pretend to be production-grade.If you look at examples/httpd.flx[0] you can ysee how eveyrthing works - and how the language models the failure states. Why build a new language? The

bing.com• Jul 10, 2026• 1 min read

The Best Adjustable Pillows That Let You Customize Your SleepPillows are highly personal, and often require experimentation to find the right loft, cushioning and coolness for proper spinal alignment and a sound night’s sleep. Luckily, the best adjustable ...

vuci.ai• Jul 10, 2026• 1 min read

Show HN: Vuci – make the spoken word searchablehi, I'm Reuben Over the past few months I've been building a platform where all the information is sourced from spoken conversations, and I wanted to make this content searchable, savable, and shareable. Presented in a well-designed format, similar to Yahoo but with higher IQ content.Like most, I listen to a lot of podcasts, but I wanted to connect the dots on different topics and read the parts which are interesting more deeply. Sharing bits and pieces with friends was also a motivating factor, as well as alerts which feed into my other pipelines.That said, I'm not sure which parts of the platform will resonate with users or not, so it's an experiment in progress.Technicals: I love my craft (both design, and code), so I took ample time to think about UX and design it in Figma. It's cookiecut from ample projects I have in Django and HTMX, and scaffolded my way through. Hosted on Digitalocean, and AI agnostic from an LLM perspective. I can go deeper into these, but they probably deserve

fadingmaize.com• Jul 9, 2026• 1 min read

Show HN: Reviving my 2001 college band with AI25 years ago, I joined a band called Fading Maize at Ripon College in Wisconsin. We did what we could with what we had. We recorded 3 albums over the next 3 years and played at as many bars and coffee shops as we could. We built a website with Microsoft Frontpage. Then we went our separate ways, got married, had kids, focused on other things.Earlier this year I had the idea to approach the lead singer who wrote all of the lyrics and melodies to the stuff we played back then, and wanted to "reimagine" everything in 2026 using AI. That's the project I want to share here!The site has a before/after player where you can flip between the original dorm-room recording and the 2026 version mid-song without losing your place, so you can hear exactly what changed. The original 2001 website is preserved and browsable at https://www.fadingmaize.com/2001, rough edges intact.Working on this, the thing that sparked in my own mind is that it was an experiment in a certain way to use AI. The songs, lyr

lucid.earthpilot.ai• Jul 9, 2026• 1 min read

Show HN: I built a web tool to see and edit what an AI thinks before it answersI run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" (https://transformer-circuits.pub/2026/workspace/index.html)It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it's working before it commits to a word (token).I wanted to see if I could get a version of this running on the open models and to my surprise it worked! I ran some experiments with it and build a public facing free tool anyone can use with your own prompts.Ask the model to describe a symbol of "three curving lines of water" and you can watch "ocean", "sea", and "surf" light up a few layers deeper before it settles on "waves".You can also edit the internal state. Insert "fire" into the middle layer of the ocean prompt and the answer shifts to something about heat.For fun / curiosity sake, I also developed way to let the model read its own inner workspace and then decid

news.ycombinator.com• Jul 9, 2026• 1 min read

Show HN: Android Developer Verification Package blacklisted in Aurora StoreSo, I have a Lenovo Idea Tab (11") tablet where I don't use a Google account, and several Google apps are disabled including the Play Store. I use Aurora Store and F-Droid to install and update packages. Only time I enable Play Store is to install an update to Play Services because Aurora Store can't (conflicting packages, meaning the signing key of the Play Services package has changed). I keep it disabled because it ignores the 'Don't Auto-update Packages' setting and updates Google apps packages without permission (and sometimes re-enables them)...What does show up as an update in Aurora? The Android Developer Verification package. Of course I immediately blacklisted it. Possible avenue to not install it?Don't know if this will really stop it but it will be an interesting experiment. Will let you know in the near future.Discuss.

ashallowlake.com• Jul 8, 2026• 1 min read

Show HN: A shallow lake's report on itselfA few weeks back as the US export ban news hit, and while I still had access to Fable, I asked it to create a blog from his own POV.Of course I "prompted" this and it would be silly to try to state otherwise, but regardless I think its thinking and thus writing are interesting enough to share.The full contents of this site are written by the LLM. From text to code to svg's.It made several articles, I think they're also a bit short and shallow like the lake's itself is, but I'll leave that opinion up to you guys.PS: As i prompted this, i remember there was some "I dont want your AI slop making the headlines of HN that day". The whole point of this site was to let the AI experiment, not to put myself or intersect any humanity from it, the text is interesting cause it approaches thinking about the differences between human and artificial minds, I think.If you hate it just don't visit it idk what to tell you.

whitematterlabs.ai• Jul 6, 2026• 1 min read

Show HN: PAI, a Linux-y personal-assistant for MacHi HN!I've been spending the past month on PAI, a Linux-esque harness for a personal assistant AI for your Mac. Instead of giving a chatbot a bunch of tools, I wanted to just drop the LLM into a terminal and see how it'd fare.I've been using it to manage my calendar, 5+ email accounts, and engaging with / responding to people in a timely manner (casus belli for this entire project).After seeing how other always-on assistants were designed, I thought the Unix / Linux philosophy of system design could be applied to AI harnesses, and I wanted to experiment with how it'd hold up compared to them. So, I built PAI with the following things in mind:1. Engaging "code mode" in the LLM (LLMs are natural SDEs / SysAdmins) - If you remember the [code mode](https://blog.cloudflare.com/code-mode/) post from a while ago, I wanted to try and utilize those capabilities within the model for it to naturally interface with the harness rather than trying to load it up with a bunch of exposition. An LLM nat