Ideas Lab

My Apple ID is locked for a week, Apple is a single point of failure

My Apple ID was locked by Apple Oct 3rd. I got an automated email stating that I will receive further instructions for account recovery Oct 10th, a week of pain. There is zero human escalation path, no phone number to call, the iforget link leads to same message as email and no further escalation.Because my Apple ID is frozen, the App Store is completely bricked. I can’t update any apps. Living in Japan, almost all of my critical banking and payment apps (like Rakuten Pay) enforce hard version checks for security. The app refuses to launch, needing update. A locked Apple ID effectively cut off my access to my money and daily transactions.My temporary workaround was digging out an old Android phone to use as a backup for my payment apps (of course these apps are only allowed on one device so now I need to carry two phones). But it made me realize how scary my setup was. If Apple decides to lock account, entire day-to-day life stops, and no one to talk to about it. Going forward I am definitely not storing any important government ID like driver license, payments cards, my number card (similar to SSN in US) on Apple devices.How are you guys decoupling your digital lives from a single OS ecosystem? What does your personal "cold standby" look like to handle this risk?My personal computing infrastructure was all in Apple ecosystem. But this incident made me realize, Apple is SPOF, I need to diversify away from Apple and be also part of non-Apple environment.

Hacker News · 25d ago · Tool · AI

Lack of a true AI-powered Google search alternative

Users frustrated with current search engines want a real AI-driven Google competitor that delivers better, more advanced results without the limitations of existing tools.

X · 26d ago · Tool · AI

Giving Opus 5.5 a simulated paint canvas

Hacker News · 29d ago · Tool · AI

I turned my iPhone and a $20 smart plug into an f-stop timer

I am a film photographer and do some darkroom printing and always wanted one of the proper, advanced f-stop timers, but never really wanted to spend a couple hundred dollars on one. Eventually I figured my phone was already perfectly capable of doing the timing, it just needed a way to switch the enlarger.So I built Darkplug around a cheap smart plug. The app controls the enlarger over the local network and does regular timing, f-stop timing, test strips, has an intuitive dodge/burn workflow, split grade (2 timing channels) and paper development timing.I’ve been using it for a few months in my improvised bathroom darkroom.Fair warning: the app was blindly vibe coded using Codex and Xcode.

Hacker News · 24d ago · Tool · AI

Are there AI models for generating sounds based on a text and reference?

I've been having a hard time finding a solution. Is there really no commercialized model that I can feed in a reference sound and text instruction and get another sound out?Right now having a multimodal inputs to image or text output is a commodotized, solved problem. IE you can put a prompt for some image and use a reference image to guide the model on what you want. After all, a picture is worth a thousand words right?Ive also used a text and audio input in order to get a text description or classification out.I cannot for the life of me find a solution for Audio + text -> AudioMy usecase is that I'm trying to generate new sound effects based on a source that doesn't have that many clean examples and thought this would be just another solved workflow but I'm not finding much. Tried elevenlabs SFX but it's only text->audio and without the reference, it's hard to guide with just text and recreate a sound with any accuracy. I tried the Stable Audio 3 model which is supposed to do what I want but the results were terrible. This modality seems to be stuck where image generation was in 2016. Is there something else or is this just not a common need?

Hacker News · 25d ago · Tool · AI

Unpredictable changes in AI model behavior

AI models frequently alter their performance and outputs over time, making them unreliable for consistent use in development and problem-solving.

X · 25d ago · Tool · AI

Minigraf – An embedded, bi-temporal graph database in Rust

A successor project to my previous attempt at building a temporal graph database (https://news.ycombinator.com/item?id=23455516). This one builds on its predecessor's concept, but drops the dependency on another database to provide the storage, transaction and query engines. Minigraf is self-contained, packaged as a library crate, embeds into your application, and supports full bi-temporality.

Hacker News · 26d ago · Tool · AI

Nightwatch – a Mac menu-bar app that tells you when tonight is clear

Here in the north of England clear nights are at a premium, and it's never guaranteed that you'll be able to see anything but cloud. That's why I developed Nightwatch, so that I could be notified when one of those precious few nights where I could see into the heavens was available. Finding out whether tonight was worth setting up meant reading forecast charts every evening, usually to learn that it was not. Nightwatch does that reading for me.It sits in the Mac's menu bar and refreshes the forecast every 30 minutes. An hour before sunset it sends one notification, and only if there is an unbroken run of clear sky in astronomical darkness long enough to image in. Otherwise it says nothing: no news means "clouds".I hope this is useful for other hobbyist stargazers too!When I was a child I wanted desperately to be an astronaut or a dinosaur. I'm now old enough to be the latter and was born in a country where the former was never an option. I've had a fascination with the stars since a a friend of my father gifted me a telescope, and have faded memories of sharing time with my father staring at the stars. My father passed away a few years back and the memory of those nights came back, along with the want to share the same experience with my kids and grandchild.The app uses two forecasts: Apple's WeatherKit is the main source and Open-Meteo is a second opinion. When they disagree, the alert says so instead of averaging them.Thin high cloud counts for half. Stacking many short frames works through a veil of cirrus, so treating it as full cloud threw away usable nights.It works on your own horizon: hills come from terrain data, and you set the houses and trees in each direction, so they are accounted for when it says what is up.It works out, a year ahead, when the Moon will pass in front of a planet, a bright star or the Pleiades as seen from your site.You don't need an account. What leaves the Mac is the coordinates of th

Hacker News · 27d ago · Tool · AI

Graphene – Data analysis toolkit for your coding agent

My friend and I have worked at a number of BI companies and thought: Can’t a coding agent do most of this now?Almost. They just need a context/semantic layer to ensure query correctness and some kind of artifact for publishing findings and visualizations.We built an open source project called Graphene that provides these tools:- Semantic layer that’s more token-efficient than YAML, more deterministic than Markdown (eg, composable, callable metric macros), with a query API that’s well in-distribution (SQL). - MDX-like files for dashboards (Markdown with inlined SQL + HTML components for viz with support for CSS and Javascript) - Connects to popular data warehouses or local DuckDBYour coding agent will build really in-depth reports and can ofc leverage any other skills or context that you've made available to it. We dogfood it inside a monorepo with our website, app source code, planning docs, etc so the agent has access to a ton of context. It’s also nice that the agent can add instrumentation, adjust pipelines and transformations, and add dashboards all in one PR.If you want to try it out, just point your coding agent at https://github.com/graphene-data/graphene/blob/main/docs/set... and ask it to set up Graphene.If you don’t have data to play with, you can clone our example project:1. `git clone <https://github.com/graphene-data/example-flights.git`> 2. `cd example-flights && npm install`Would love any/all feedback!

Hacker News · 29d ago · Tool · AI

Project shutdown : can we help?

Hi! I'm thinking that we can help the the project to survive and help us to maintain the integration with home assistant alive. We are a lot of users, and we can massively write to Haier Europe. The project damage Haier? It's a little hilarious.. Anyway.. What do you think about a creation of petition or a common email to Haier?

GitHub · 2y ago · Tool · AI

AI search for every photo and every frame of video on macOS

Hacker News · 27d ago · Tool · AI

Made an open-source Lego AI generator

Hi there :-) New on HN, first time posting.Past year, around December, I started experimenting with making ChatGPT and Claude generate source code in LDraw language.This LDraw is literally an "assembly" language, a low-level programming language that describes how to assemble LEGO pieces together into models, one placement instruction at a time.When executed by specific tools, like e.g. LDView, LeoCAD, Studio... these instructions become LEGO CAD models, that can be interacted with, modified, etc.Or, in other words: one LDraw source file in .mpd or .ldr format is equivalent to one LEGO CAD model.So, the idea I had was: if I manage for maybe ChatGPT or Claude to generate high-quality LDraw source files... then, they would actually be generating high-quality LEGO CAD models, right?Then, after months of iterations and trying one thing after the other... it worked!!!Long story short: using GPT-6 Astra and Opus 5.5, I've managed to create a python toolset, instructions, and docs for agents in general. Now, these can be used by them to generate LDraw models.I've packed it all as a dockerized web app for others to try and experiment, with several providers (and agents) to choose from: OpenAI, Claude and OpenRouter.Here's a bunch of exmaples: https://anteloc.github.io/index-samples.html.If you are curious about the internals of an .mpd model, the "what was the agent picturing on its mind", open the .mpd file that got your attention on a text editor, and read the first line under the ones starting with "0 FILE".I'd really appreciate feedback and comments, let's see where this goes =)

Hacker News · 28d ago · Tool · AI

Offrun – manage every coding agent from one workspace

Run Claude Code, Codex, AGY, and Grok Build side by side. See who is working, who needs you, and what every account has left.

Hacker News · 28d ago · Tool · AI

Pi pod – Run your pi coding agent in sandboxes on your own server

pi pod runs sessions of the pi coding agent in isolated sandboxes ("pods") on a server you run, in composable environments.----Since moving my company towards AI-native work, I have been really frustrated by the state of "agentic engineering" environments. Products by the labs (claude code, codex) lock you into a single provider for your tokens. Agnostic solutions (factory, devin, arguably cursor) make you pay per-token costs. None of these products allow you to fully customize the harness, and of course they all run on someone else's infrastructure.I've been an early and fervent user of pi, which I think is fantastically simple and beautiful software. I have felt it needs an environment for it to work across platforms with fully functional composability for teams.This is very much a work in progress, but for my team this has been a much needed solution and has helped us tremendously. I hope you will give it a try and let me know how you would like it to improve.

Hacker News · 28d ago · Tool · AI

What 482 hospitals charge vs. what insurers pay, from their own files

US hospitals must publish a machine-readable file of their prices, including the rate they've negotiated with each insurer. The files are huge (one is 36GB), in four formats and often messy, so almost nobody reads them.I built a crawler that finds each hospital's official file and pulls out 29 common services. Across 482 hospitals: a moderate ER visit is listed at a median $1,285 while insurers pay $288; a metabolic panel is listed at $207 while insurers pay $11.46.To keep it honest: only per-service fee-schedule dollar rates count (no case rates or percentages, which cover a whole visit), each figure needs at least 3 insurers, and every value is checked against Medicare reference rates. Surgery is excluded because insurer surgery rates cover the whole operation while the list price is one line item. Each hospital page links its source file. Feedback on the methodology is very welcome.

Hacker News · 29d ago · Tool · AI

Is anybody producing good code with coding agents?

This is a genuine problem that I hear from senior engineers. I'm looking for a solution.--The quality of ai-generated code is <censored> (claude, agy, copilot, codex a little better).It's exhausting to read.I used to love learning from my experienced colleagues and taking pride in what we made. We spent time on elegance and craftsmanship.Now I spend nearly the whole workday slogging through convoluted code riddled with footguns. I ride on hopes and dreams I might understand a changeset.It takes 5x longer to review Claude merge requests and I barely understand what I approve.Each day I drift further from understanding as I shovel the same <censored> into the codebase.The solution seems to be, reach "level 4 autonomy" and don't read or write code anymore.--WHO HAS SOLVED THIS PROBLEM? PLEASE HELP!

Hacker News · 28d ago · Tool · AI

No easy way to manage multiple personal AI agents like Cursor

Users want a 'Cursor for personal AI' with available agents (muse, instinct, dot, grokbot) but currently lack a unified tool to switch and manage them seamlessly.

X · 28d ago · Tool · AI

Yantra – an LALR(1) parser generator for C++

Yantra is a C++ parser generator: lexer, parser, and AST walker all generated from one tool. It builds the whole AST first, then walks it.Most LALR parser generators (Yacc, Bison, Lemon) run your semantic actions during parsing, as each rule reduces, bottom-up.That means at the time a rule's action runs, you don't yet know what its parent looks like. This pushes a lot of grammars toward hand-built AST classes and a separate walking pass whenever you need to look ahead into siblings or defer a decision until more context is available.On the other hand, Yantra always builds the whole AST first, then walks it top-down in a separate pass, calling your semantic actions as it goes. A parent rule's action can run before its children are visited.A single grammar can define more than one walker. For example, one that emits C++, another that emits Java, from the same parse. The AST and the walker classes are both generated for you.A small example (full version, with compile commands, in the README): start := expr; expr := expr(a) PLUS expr(b) %{ std::cout << "Adding" << std::endl; %} expr := NUMBER(N) %{ std::cout << "Number: " << N.text << std::endl; %} NUMBER := "\d+"; PLUS := "\+"; WS := "\s+"!; Running this on "1 + 2 + 3" prints: Adding Number: 1 Adding Number: 2 Number: 3 The outer "Adding", the root of the tree, prints first, before either of its children. That's only possible because the whole tree exists before any action runs.Some other things about it: integrated lexer with mode support (for things like nested comments), an optional amalgamated single-file output mode with a generated main(), C++23, MIT licensed.It's young (0.5.1, pre-1.0) and single-maintainer, so treat it as early. I'd rather know what breaks than have it look more finished than it is.Known gaps are listed at https:/&#x2

Hacker News · 1mo ago · Tool · AI

Open-source model routing for coding agents at Astra-level performance

A few months ago we started building a model router for coding agents because we thought we could outperform any single model with an ensemble approach. Recently we’ve achieved that milestone and I want to talk about how we did it.First of all, a quick explanation: the Weave Router (https://github.com/weave-os/router) plugs into any coding agent (e.g. Claude Code or Codex) and intelligently switches between LLMs. So, for example, Astra handles tricky debugging or complex system design tasks, and Deepseek v4 Flash handles simple frontend updates.What we’re announcing today is our new routing model, which we’re calling Weave Router 2.0. We benchmarked 2.0 against GPT-6 Astra on Terminal Bench 4.0 and SWE Atlas. On both benchmarks, the router had equivalent pass rates. On Terminal Bench, the router hit 52% of Astra’s cost, and completed tasks 2.2x faster. On SWE Atlas, the router cost 54% as much as Astra and ran 2.5x faster. (Full results on our website at https://weaveos.com/router!)It turns out training a model to route effectively - taking into consideration model capabilities, costs, cache awareness, and more - is a really hard problem! I want to talk about three ways we were able to improve so much over the last few months: 1) a new architecture, 2) larger training data set size, and 3) smarter cache-eviction impact calculation.1) a new architecture. Our initial approach used an RL model without many priors. While RL is still an important part of the story, the cost of fully exploring the space of routing decisions is very high, so we’ve taken some shortcuts that have significantly improved performance.Consider how large the search space for the routing problem is. Take a typical coding agent session, with ~100 agent turns (i.e. 100 LLM API calls). Technically there are 100 chances to select a model. If we assume a roster of ~10 models (of course there are lots more but we can remove any that are Pareto dominated), then there a

Hacker News · 1mo ago · Tool · AI

Rhun, an open-source code editor written in assembly

I found that I'm not using even 1/3 of vim/vscode features anymore.That's wht I'm building rhun - a small code editor for Linux, Windows and Apple silicon Macs. It obviously has Vim mode, a terminal, Git diffs and a panel for Claude Code or Codex sessions.The editor and pixel renderer share an x86-64 assembly core. For Apple silicon, a build-time translator converts that core to AArch64, with separate platform adapters around it. The latest release can draft commit messages using a local Ollama model or an existing Claude Code or Codex subscription.It's a solo project, MIT licensed and still early.

Hacker News · 29d ago · Tool · AI