Ideas Lab
Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
- Ideas
- 4,820
- BUILD
- 702
- Sources
- 8
- Last sync
- 2h ago
Problem of managing type 1 diabetes without AI assistance
ProblemHunt1y agoToolAI
Simantic (YC F26) – Firmware Simulation for AI Agents
Hi HN, we're Ahnaf and Seungmin from Simantic (https://simantic.com). We are building the simulation layer that lets engineers and AI agents test and validate firmware without hardware.Before Simantic, we were ex-firmware engineers at companies like Neuralink and Tesla. We’ve worked on some of the coolest projects, like the Cybertruck and Roadster, back when they were still early prototypes.We started working on firmware back when ChatGPT didn’t exist yet, but over the years, we saw how much of the engineering and development work has been automated as the frontier models improved to this point. In software, AI can run and test code inside your computer in a matter of seconds. But as firmware engineers, we didn’t have that luxury. An AI agent can write firmware in seconds, but in order to test it, we had to flash a physical board, then manually run tests using expensive and clunky tools with software made over a decade ago.To speed up the validation loop, we built the simulation layer that lets AI agents test the firmware and make decisions based on evidence, instead of waiting for the engineer to run tests for them. We used to spend hours testing our firmware manually on devboards, but now we use our own simulation to validate firmware in seconds.What we offer: - Virtual devboards you can program and run with a single API call, without leaving your terminal. - An AI code reviewer for firmware, that makes informed decisions based on evidence, using our simulation as a verification engine. - A CI/CD pipeline for your hardware projects that validates your firmware against a simulated version of the microcontroller on every commit.Here is a demo of our simulation used in an AI code review session: https://www.youtube.com/watch?v=kBK1ZjGWWbQOur users are using Simantic for bare-metal and RTOS development for applications like flight controllers, electric vehicles, robotics, and satellites. For safety critical systems like avionics and
Hacker News1d agoToolAI
A proof-of-concept formalization of the IRS federal tax forms
The linked repo is 100% vibe coded, but it was built on a handful of principles:- Most tax software derives trust from the party who maintains it (e.g. Intuit, the IRS, etc.)- Vibe coded software lacks this trustworthiness.- Therefore any formalization should build in verifiability and mechanisms that make it possible for users/maintainers to trace claims/interpretations back to authoritative source documents.It's very much a back-burner passive project right now (do not use this for anything real!), but I feel strongly that something like this ought to exist for the public good. I built it to get a sense of what the shape of what such a thing might be.
Hacker News2d agoToolAI
SlideBySide – Present slides without sharing your screen
Why is it useful? - Present slides without sharing the screen and have every one be on the same page. - Present together with other cohosts and all control the current page. - Other features such as presentation collab features.Why should I not just vibe code my own solution? - Its a hassle to maintain a version online.
Hacker News2d agoToolAI
Do you still read clean code and software architecture books?
Now that we have coding agents writing all our code for us, are you still needing to reach out and read books such as clean code and other software architecture books?I think they are now more important than ever as there is more code being pushed out than one can read to see if it is robust as the agents claim.
Hacker News4d agoArticleAI
Lack of test mode/sandbox for AI agents to safely handle purchases and refusals
AI agents making real purchases lack safe testing environments with fake stores, trap invoices, and scoring for incorrect refusals, risking financial errors in production use.
X3d agoToolAI
ADRs for AI – Deliberation records for human–AI work, versioned in Git
Why is this worth your time? Essentially, this solves two problems of AI-assisted programming:(a) the first problem is how to do oversight and what do oversight of and this is solved through the ORRCF (for Options, Recommendation, Rationale, Confidence, Falsifier) question format (in which models are supposed to surface all their doubts with fully fleshed out recommendations, with falsifier, to be approved or overridden)(b) the second problem is how to scaffold sustainable AI-written code; the ADRs (Architectural Deliberation Records, after Nygard's decision records) written by the models, summarize all the thought process involved in any design decision and provides the blueprint for the code.In tandem, the records provide both the reason why certain non-obvious design choices were made, from a constant, to a library choice, to an ordering in an operation; and also under what conditions different decisions would be made, for instance, in a different platform, or under different latency requirements, or for a different audience, and so on.This is a framework I've been working for over a year, that is the starting point of all my projects. It involves a lot of moving parts and my challenge is figuring out onboarding. I'm hoping the plugin, ADRs4AI/plugins, just created and now also submitted to Anthropic's marketplace, will make it easier. I am also in the process of recording introductory videos.I would like feedback on the onboarding, on what you make of the currently online materials, and how I could make any of this clearer. Thanks!
Hacker News6d agoToolAI
Hob - Open-source, on device alternative to Claude Cowork and ChatGPT
Hey HN, I'm Christian and this is a new OSS project I've been noodling on for the last couple of weeks. Hob is a free, MIT-licensed desktop app for Mac, Windows and Linux that works on your files the way the Claude and ChatGPT desktop apps do, except the model runs on your own computer. It uses open-weight models (currently Gemma 4 and gpt-oss). All your chats and files never leave your system. The only things that go online are web search (can be turned off in settings) and any MCP connectors you add yourself.Main features:- Automatically finds the best open-weight model for your hardware on first install (Mac/Linux/Windows)- Writes sandboxed Python code for ad hoc tools (data processing, document conversion, graphs etc.)- Built-in web search (powered by SearXNG)- MCP support- Image recognition- CRUD to your local filesystem- Works fully offline with no internetBefore building this I tried every local AI app I could find, but it seemed each one had different problems. The main thing I noticed is that none of them could do what the ChatGPT and Claude apps do with your files, e.g. read and change files in a folder, look at images, run code in a sandbox, draw a chart. The most advanced thing any of them did was paste a plain text file into a small context window, which basically failed as soon as you had a file larger than a few KB. I couldn't find anything that could easily parse images and bigger PDFs.The OSS solutions that were more advanced all seemed to default to hosted models (either OSS or closed), which defeats the entire point of the privacy that on-device OSS offers. They also seemed to push towards an account/open-core style business.I build it using Electron bridged with llama.cpp in its own process. On initial load, the system will try and figure out if you have a compatible graphics card and if not default to CPU-only (I ran into a lot of issues of graphics card beeing seemingly compatible but then crashing on first query,
Hacker News4d agoToolAI
Is it not possible to enroll for Apple Developer anymore?
I've been trying to enroll for Apple Developer for over a month and nothing works.The Apple Developer app won't accept my Canadian passport for identity verification. The enrollment is for a Delaware LLC, so my Apple account region is set to US. I can't switch the account region to Canada either, because I haven't lived there in years and don't have a Canadian bank card.If I enroll through the website, the enrollment gets approved, I accept the term and, when it's time to pay, all my cards get declined. I tried ~7 bank cards (debit, credit, personal, business), all with matching billing addresses. All US cards. All the banks tell me they didn't decline transactions from Apple. I tried no VPN, VPN and residential VPN. I tried from my MacBook, iPhone, Safari, Chrome, incognito, non-incognito.Phone support is unavailable every time I check. I tried talking to regular Apple Store customer support but after repeating myself over 5 times with different agents, the last person I got transferred to told me they couldn't help with Developer stuff.If I email Developer support, they reply ~5 days later with unhelpful canned responses like "have you tried Safari incognito?", "you should try the Developer app instead" or "make sure your billing address matches your bank information". I'm at support email #9 and enrollment attempt #3.Has anyone had similar issues and been able to fix them?
Hacker News5d agoToolAI
Tool to detect and identify AI-generated content usage
With growing use of AI content generation, users and organizations need easy tools to detect and verify AI-generated text or media to ensure authenticity and prevent misuse. [Google Search suggestion]
Google Trends5d agoToolAIUS
User-friendly AI simulation tools for robotics education and prototyping
There is growing interest in using AI agents to teach robots skills in simulation, but current tools are complex and fragmented. A simple digital tool for hobbyists or educators to experiment with robot AI in simulations is needed. [Trending: "nvidia microduck" with 200+ searches in DE]
Google Trends5d agoToolAIDE
Tool to track and alert on AI cybersecurity risks
AI cybersecurity threats are increasing and complex; a tool providing curated, real-time alerts and mitigation advice could help businesses prepare. [Trending: "sam altman" with 200+ searches in BR]
Google Trends5d agoToolAIBR
Hurston-1 open source TTS that speak Southern American and Afro-English
Hey HN, I’m open sourcing my Hurston-1 narrowband TTS model (Apache-2.0). It is very good with American English and does especially well with Southern American and Regional African English accents. Destined AI is based in Atlanta, and I built this because I’m amazed by what AI can do, and I wanted to help introduce and welcome more people to feel comfortable using and interacting with AI.Since 2021, I’ve been collecting fully consented voice data from over 20,000 people, 1M audio recordings, and over 1,800 hrs of audio captured to date. For this model, I used a small part of the data, 136 hrs, to finetune Maya1 and expand it’s capabilities.Hurston-1 is a narrowband TTS model that focuses the output on telephone use because that is still where most of these voices will be heard. I’ve used it to support customers such as Amazon and Salesforce and generated over half-mill revenue with it. Now I’m open sourcing it to help unlock opportunities for others as well.Limitations: this model doesn’t maintain the exact same voice across prompts and doesn’t support voice cloning. For many use cases, this is fine but maybe not so - if you’re creating podcasts.This is the first release - I’m already working on the next version with improvements.I would appreciate, if anyone is interested in this space, download the model from huggingface, check it out and let me know any feedback. Also, open to connecting with others in this space as well.
Hacker News6d agoToolAI
We had AI write a wiki from 45k Enron emails, every fact cited
Hacker News7d agoToolAI
Impossible Machines: declaratively program the physical world
Hey all —Sharing a thought experiment I put together. The premise: what might declarative programming feel like for the physical world?We’re already familiar with this paradigm in software land (eg SQL etc where we declare what we want and the execution engine figures out how).I didn’t have access to an actuator so I mocked up the concept in software. The way it works is you demonstrate the effect and the system figures out how to achieve it. So say you want to ring a bell and you have a crank. The system will find a way to connect the two. If you add obstacles it figures out how to work around them (runs a constraint solver runs behind the scenes).I think what’s interesting about this is being able to think about the problem at a higher level of abstraction, with the system figuring out a way to achieve the intended effect.Anyways, curious to read reactions, feedback, and interesting ideas on how to extend this!
Hacker News8d agoToolAI
Need for reliable coordination and verification of multiple AI agents
Individuals and organizations struggle to keep humans in control when coordinating multiple AI agents, verifying outputs, and ensuring reliable infrastructure.
X6d agoToolAI
Corgi, a helpful {agent, terminal} multiplexer
Hey everyone,Inspired by Herdr, I've built an agent multiplexer that I've been using as my daily driver for a few weeks now.I think I improved on the concept in a few ways, focusing on the ergonomics I always wished I had:I show you what the agents are up to, along with a running feed of their activity. There's also a simple shortcut (F1) to go to the next unread agent.I use multiple accounts, so I've added unified launcher for Codex/Claude Code/Pi. Theres some careful ergonomics there: fast search and resume over sessions, inline usage tracking etc.Many small quality of life improvements to the terminal experience: - Links can be copied with a click, so no need to drag-select over many lines - cmd+v just pastes images (even on SSH) - images have a thumbnail preview. - Built-in CPU/Memory/GPU usage tracking, broken down by workspaceI assume you have access to cheap inference (Luna/Haiku/etc). It just reuses the agents to organize things for you: what is this http link? what is this worktree about? what is each agent doing? It's small but it made my environment feel more cozy.On a personal note, I've been on a frustrating sick leave for a while now. I created Corgi to challenge myself, and see if I can go back. The answer is more mixed than I had hoped, but I am happy with the result and thankful for the experience.I hope you like it! a few friends & myself have been using it for a few weeks and it's been pretty nice. There's still a lot to improve and some rough edges, so feedback would be greatly appreciated.Thank you :)
Hacker News7d agoToolAI
OnKey – I'm a bad singer, so I built an app to show where I'm off-key
Hi allI was pretty terrible at singing, now I’d say I’m bad but not terrible. This is because I’ve been using a singing app (won’t name it here) that scores me on my pitch and timing throughout the song so that I can improve.Lately however, the app I’ve been using has flooded their song list with songs that aren’t originals. I didn’t like this at all as for me, it’s easier to try to improve when you’re singing along to the original.So, I asked an agent (Claude Code) if it could write some code to listen to Spotify and also listen to me and see if it could detect both pitches and score me. It impressed me by writing some Python and showing me my pitch in the terminal!It couldn’t go all the way though and detect the singer’s pitch in real time.So I found the next best setup and built OnKey, a Mac app that needs to listen to the song once (it doesn’t save it) and then when it’s learnt the song (takes a couple of minutes), you can sing along to the pitch track that it’s learnt. OnKey is free to use and open source under the MIT license.It can listen to Spotify, Apple Music, and YouTube playing in your browser with the right permissions.During the build I found that someone had done something similar in Nightingale, but this requires a library of songs exported to disk and who has this in 2026 (maybe some of you ;) - but we need to help the normies too).You can check out a demo video on the site of me singing (warning given) here: https://singonkey.appThe app sends out to find the song info (short Shazam fingerprint, and looks up song details), lyrics (from LRCLIB), and checks for updates.The app never sends the music (it doesn’t save this to disk) and your voice. Everything you’d expect to stay private does.It’s still weak in a few places:- when the song’s backing is noisy it’s hard to pick the pitch track out- sometimes it gets a note an octave off- it’s limited to Apple Silicon Macs, M1 or later, and only macOS 14.2 up because extra drivers aren’t required p
Hacker News8d agoToolAI