alt Hacker NewsAsk HN: What are you working on? (August 2026)
What are you working on? What have you been curious about lately?
Comments
Building a Web-based guessing game called „Guesstimate“ where the player needs to guess age, capacity and height of things. Includes friends leaderboard and player‘s statistics:
Keep hearing that management sucks so building a tool that helps new and experienced manager improve and grow.
Harness evals on private benchmarks. I haven’t found a good way to evaluate harness releases on realistic private tasks
still trying to figure out how to find users for my offline model agent harness with self-customizability and an offline wikipedia reader/tracker. tell your friends if you can think of a meaningful audience profile. http://enough.support has details/links
Got laid off in June. Grinding leetcode.
a new agent/harness, mu. not ready yet but hope to let people play with it ~soon. its got very few novel ideas, but attempts to do the existing good ideas reasonably well and be as minimalist and composable and pragmatic as possible
I've been building a cicd + orchestration layer, and on-off hacking a 2d animation engine.
It's a bookmarker tool.
A few things outside of normal work that are deliberately different to be interesting to me:
- Ongoing work on an airline announcement engine that works with flight simulators
https://github.com/fearlessfrog/MSFS_Universal_Announcer
- A multiplayer board game for Discourse forum users that is not the popular Risk (tm).
https://github.com/fearlessfrog/discourse-not-risk
Both have a fair bit of traction, but is often the case, keen to do something new this month.
As a side project, I've been working on a RAG/MCP/agent service with workflows, for security: https://mappedsky.com/seizu/
This primarily builds on top of cartography (https://docs.cartography.dev/), which I'm a contributor to, which pulls infrastructure, SaaS, etc info into a Neo4j database, makes edges, and has a standardize ontology, so you can do attack path analysis, vulnerability assessment, inventory, etc.
Seizu uses the RAG built by cartography, and adds reporting, graph exploration, automations and more on-top of it. It currently ships with a couple pre-made automations:
* Automatic dependency vulnerability fixes, like dependabot, but uses codex/claude/opencode in a sandbox to do so, which ensures it doesn't just bump a version in the file, but actually assesses whether the changes in dependencies need code updates, and gives you a thorough overview on if changes aren't needed, and why changes were needed if so. If tests break, it also watches and fixes them automatically. * A workflow to run the cartography sync, making it possible to split apart the stages, run portions of the sync on different schedules, in parallel, etc, while also making it possible to properly trigger downstream syncs, or other types of workflows. * Generic AI agent workflow, which can be staged, run in parallel, or chained together via inputs/outputs, using Seizu's own custom agent (which has good LLM provider support, sandbox support with files, etc)
Workflows are built on-top of temporal, allowing it to be quite flexible.
An open source, decentralized, interoperable marketplace backed by open-source SaaS for every vertical
I'm working on a Python rewrite of Anacreon: Reconstruction 4021.
A philosophical task manager, based on notable philosophers such as Baudrillard, Foucault, etc. It's been a fun game of reading these works, trying to distill their essence, and putting them through the LLMs to see what comes out. Currently it's not one task manager but rather many prototypes, and I'm trying to reconcile various design issues. In the same way that Marx's "philosophy" is essentially a "praxis" of political and economic power, which does not presuppose a "truth" but rather creates one, my task manager is a pragmatic tool for establishing the meaning of life.
My dotfiles.
Specifically, I'm working to stop working on them.
update to my ai first desktop https://apps.apple.com/app/aifcc-ai-first-computer/id6782364...
Making rent as an open source developer.
Desperately trying to attract new monthly sponsors and people willing to buy me the occasional pizza with my terrible HTML skills. Is it working?
If any individuals, companies (or bitcoin millionaires) would like to help a long-time OpenBSD slacker, unslack, I'd really like to focus more of my time on open source development (and advocacy), rather than making rent. Feel free to contact me.
https://brynet.ca/wallofpizza.html
(Native SegWit): bc1qwe6zv0ezq4gzlea6tw45qhsn5kckheljn0krvt
3dpack.ing
I'm working on an autonomous snow clearing robot: https://www.frost-e.com/
The basic idea is that instead of trying to solve the general case in robotics (ie, the humanoid companies - multiple tasks, multiple environments, generalization, etc) which needs billions of capital, can you efficiently deploy current tech to robustly do one task in one environment for cheap.
I'm on paternity leave and I've been returning to a host of LLM driven projects;
They are all for me, with a small interest in commercializing some of them as a hustle.
Project: a local version of Claude Co-work for document organization, one of my original projects that I wanted from back in 2024, so it could help me find everything on my hard drive and turn it into a knowledge graph/mind map without sending everything over the cloud. Bonus for removing duplicates/disk cleanup.
Project: Memoria - an SMS based daily journal - my first platform! security, interoperability, yay! This started out as something for my wife to make notes on the kids milestones with an SMS reminder, but then I have ADHD type memory issues and wanted a voice based journaling system so that I could just narrate about my day and have an AI clean it up. At the end of the week it makes a little email with photos, etc for a week in review. Next step is a big lift if I want to format everything to be put into "baby books" because of the print publishing workflows.
Project: Curio - based on the platform above - helping to declutter based on capturing the sentiment of an object. My ADHD means that my memory is trigger based, and if you toss the thing, I lose the memory. I'm trying to find a way to get rid of things without losing my memory that comes from holding it in my hand.
Project: Deep Signal - an AI driven daily podcast that gathers AI papers and news based on my interests, then transforms that into a 15 minutes daily news segment. Started out on Google's platform, now just using Kotoro and Gemma 4.
Project: Book Explorer - like Sparknotes for non-fiction. Pushes everything into an ontology for non-fiction so that it can summarize it and make it very easy for me to "skim" books that I otherwise don't have time to read. Also helps me to deep dive into particular areas. This is probably one of my most frequently used tools.
Project: Meeting Notes - Before Granola existed, this was a local granola clone that used whisper. Only later did I find that the real gap in making this work seamlessly without the janky MIDI Audio Capture was that if it was a "signed" app it got access to much better resources.
Project: Hunch - a new type of trivia app that is based on bias and a "sense" of what is true. Made so we could play trivia across multiple education levels and generations with everyone still having fun. Still in development.
Project: Drucker MCP - using an MCP to inject prompts from a custom "library" so that I could steer a big model towards as multiple opinionated experts. Meant for business / entrepreneurs - I want to think like Peter Drucker, Alex Osteralder, Rogers, Scott Anthony. This one is the one that I hope can "make a dent in the universe" because I could make it freely available as an MCP and it can help micro-entrepreneurs in the Global South.
Project: personal finance app. keeping it local.
I suppose to get the triple crown, I need to make a work out app so I have "journaling", "fitness", and "personal finance." Or could be a to-do app. lol
Heck, most of these are still in development - but the Audio Capture was abandoned for freeware.
wellbody.me - a simplified approach to body health. we condense a progression system into 3 daily actions to keep you focused on your goals.
I'm working on a pet website, but I don't know why I can't comment or submit content here
Giving another round of attention to a CLI tool for handling RSS feeds. Over the years I've evolved several automated ingest flows, most of which are fed via RSS. For a long time, I used a setup based on rss2email, but it was baroque. Meanwhile, tools of a more standard design, like elfeed and newsboat, do not cater to my use cases. So, I wrote something that handles only feed management, fetching new items (i.e., <item> or <entry> elements), tagging, and searching the database. Other issues, such as download and storage of content, tagging policy, storage, and indexing are left entirely up to the scripts for which this is a building block.
working on building a bench for human ICs for hiring
Using AI to mass scrape the internet for family accounts of Hitler's escape, to prove he made it to Argentina. I started off very skeptical but now I think its 60-70%.
I'm just about done with https://RSSVault.org, a curated RSS feed directory.
Password is vaultearly644988 if you want to check it out.
The companion app, a widget-first RSS headline viewer called Just The Headlines is just about done too. Site is online if you want to see screenshots: https://justtheheadlines.app
I'm in the (required, sigh) closed test phase of Google Play Store approval. Drop me a line on X (https://x.com/JJordan) if you would like to join the test for that.
Feedback is more than welcome.
RapidCAM.app is still taking up all my time. It is a 2.5D, parametric CAD/CAM program for CNC and laser with flat or 4th axis. Open source, free, run completely in browser.
This is a passion project that I want for my own use but am happy if other's find it useful and very open to feedback and collaboration.
The file system is open and very well defined so that AI can write files. There is an AI Assistant dialog that helps you to write prompts and then takes the AI file and runs the file through a solver and checks.
A slop detecting browser extension for LinkedIn because I have to use it these days to find a job, I was getting tired of seeing all the AI slop content.
Working on putting together a self-paced "Coding with AI" course for non-SWE(s).
Since I could not find anything out there, I am scratching my own itch.
TermDOM: A terminal renderer which used real DOM nodes, so you can write TUIs like web apps with HTML, CSS, and whatever framework you want. I didn’t really write this, more like spent intense weeks of effort where I product manage (yell at) Claude and did visual testing.
A Golang web framework.
https://github.com/gofabrik/fabrik
I’ve been waiting for a spine surgery and to do something with my time I started experimenting with an idea I had. It completely pulled me in, and helps me to distract myself.
It is work in progress, lacks of documentation, I am not even sure I will release it.
Mostly hardware.
A cheap rowing counter. Competitive rowers use a training device that counts their strokes per minute. I figured out that the major parts are really cheap, even as individual purchases, so I wanted to build a budget version. So far it counts strokes fairly accurately and I've just completed initial tests of the display.
Drone experiment. I'm building a image recognition drone from scratch. It's based on a H743 Slim V4, with an RPI5 and a OAK-D Lite. I'm currently trying to figure out why the back left rotor is producing way too little thrust.
Like everyone else, I'm also working on an agent harness. tl;dr I don't trust any agent to not be dumb, but the agents seem to have some success recognizing when the work of an other agent is dumb. In early tests, the back and forth seems to provide more stable and better results.
Building a repairable e-bike battery at https://infinite-battery.com
Working on goldy: https://github.com/koubaa/goldy
A new kind of GPU library written in rust with backends for CUDA, DX12, Vulkan, and Metal (tenstorrent and wgpu are planned) and bindings for rust-dynamic, python, c++, c, and dotnet (Java and Fortran are planned).
Uses the slang shader language exclusively. All submissions are expressed as graphs (like cuda graphs), are retained automatically (sometimes partially with a graph partition algorithm), and automatic synchronization of GPU resources. No runtime dependencies (slang is vendored) and new calling convention for shaders using a virtual entry point that allows resources to appear as arguments to the shader 'main'. Includes automatic VRAM and resource recycling for device resources.
Shader coroutines, rust shader authoring, and automatic kernel fusion are planned.
Supports both GPGPU and graphics.
Made it because cross backend GPU libraries usually either target lowest common denominator or are specialized for either compute or graphics or ML. In my experience GPU programs and frameworks are written to target a different kind of machine than a tape machine, but nobody outside of tenstorrent have bothered to describe that machine. So I defined a new kind of abstract machine for cooperative resource-oriented computation called a Fondaco machine for which goldy is the reference implementation.
My games, and cleaning up my ext3/4 journalling code for the NetBSD kernel. I've got it opening, reading, and replaying the journal upon mount, now I need to move on to getting it to actually log disk transactions during use.
I make a podcast client for iOS that detects and skips ads for you using an on device model. This allows me to sell without a subscription. I am working on v2 which will bring support for video podcasts and YouTube podcasts.
I'm building a language with AI as a personal project. My hobby is tinkering with my homepage [1], and for paid work, I'm handling a project related to autonomous drones
Sun signal. You can time your life events with the sun: think optimize work time, sleep time, rest time by following sunrise, solar noon and sunset.
It was my counter cultural bet to burn out and AI vibe coding all night long. Has worked pretty well.
Software Factory. MIT licensed. runfusion.ai
I put together a nationwide (US) land parcel dataset over the past year and a half, and have been building a bunch of apps on top of this data: https://landstats.com
I've continued working on my game project, Vestiges, which is a 2D narrative strategy rogue-like in Godot.
I'd hoped for a more meaningful update from when I first mentioned Vestiges last month (https://news.ycombinator.com/item?id=48884984). But I've often felt discouraged and haven't worked as much as I'd intended.
As was recommended by guiambros last month, I started the process of setting up Vestiges on Steam, but that's still in progress (currently, my identity is being verified). I also set-up at micro.blog (https://ksaun.micro.blog/) and (https://mastodon.social/@ksaun), but haven't posted anything yet.
I bought a Linux laptop for this project (I was working on a 2020 Surface Book 3). (I had used Unix in the 1990s, but not much since then. The video game industry being so Windows-centric, I'd stuck with that OS throughout my career.) So recently I spent a few days enjoying (not sarcastically!) setting up my new computer and work environment. In doing so, I also took improved some aspects of my development process.
Limited meaningful work on the game itself. From a technical perspective, I could release the demo now, but I'm dissatisfied with the content (specifically the writing). Not that it needs to be amazing just yet, but I want it at least less embarrassing. As I've worked with some of the best game writers in the industry (in my opinion; people like Chris Avellone, George Ziets, Neal Hallford, Brian Mitsoda), I'm accustomed to quality that exceeds my personal ability. And this writing work requires greater focus than I can usually muster, so I've been procrastinating, polishing other things that were already sufficient to ship.
Since last time, I've finished most work on tutorial features and content as well as the other implementations I wanted for the demo. For the modes that are ready, I added full support for keyboard-only play (which was a more substantial effort than I'd anticipated, taking close to two days (very part-time for me, but Claude was fairly busy)). I also now have an MCP server implemented so that Claude can playtest as a player would, but I've only just started to make use of it. (And some progress on the aforementioned writing, just not much.)
I'm working on a guidebook. Not putting it online to get scraped!
My health
Avarand, a classic WoW like mmorpg
Northstar web browser :)
My home media server! I’m so rookie compared to many of you, but proud of what I’ve got. We’ve (family) been on it with no paid streaming for 18mo now but it really became turnkey/low Maintenance a few months ago.
Still on plex, next step is Jellyfin.
Olympic wrestling education tool.
Indexing multiple captured video streams with awarded action points and adding athlete/referee positions overlay. Stretch goal -- controlling PTZ camera for predictive capture of the high intensity actions.
I am not really working on anything new as such, but I am mostly just polishing existing workflows. For instance, the task for today will be to use mechanize (in ruby) to automatically tap into a webservice which I use manually right now via a browser interface. I want to do this all from the commandline next. (Ideally I'd not want to depend on this and do it locally, but it does various things with .pdf files which I have not yet been able to do myself. ghostscript is surprisingly awful, and while there may be alternatives, I am not too familiar with all of what they can do, whereas the webservice really has all pdf-related tasks already solved, as-is, including optimising for size. For some reason ghostscript produces much worse results, from A to Z.)
Nothing too interesting though.
I have more interesting projects, but these have to come after I focus on more pressing reallife requirements; on my next todo list, though, I want to extend the code I use to compile from source. I track almost 4000 programs already and can compile most of these (for some reason GCC 16.2.0 does not want to compile today); I want to extend this, finishing an automatic build of the linux kernel and full bootstrap into a new system while also adding more language bindings, such as lua. And also allow for this to be compilable via a web-interface.)
I just released a small app called Fogpane: https://asok.github.io/fog-website/index.html?lang=en
The concept is intentionally simple: you open a photo, it gets covered by a layer of fog, and you use your finger to wipe the fog away and reveal the image underneath – a bit like drawing on a fogged-up window.
I’ve always wanted to publish something on the App Store, so I decided to use this as an experiment: how far can I get while letting AI write the entire app?
For full transparency, essentially all of the code was written by AI. I guided it, described what I wanted, tested the results, reported bugs, and made product/design decisions, but I didn’t really write the implementation myself.
For an app this small, I was surprised by how far this approach got me. It wasn’t completely hands-off – there was plenty of iteration, especially around making the fog and water droplets feel somewhat realistic – but it went from an idea to an actual app in the store.
I’m a software developer myself, which made the experiment particularly interesting. In many cases I understood what the AI was doing, but deliberately tried not to take over and write the code myself.
I installed Codex around three weeks ago. It’s hard to estimate exactly how much time I’ve spent on the app since then, but it’s probably been a couple dozen hours rather than hundreds.