Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git https://bit.ly/4BJa8DB

Show HN: 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! https://bit.ly/3W76mDv October 25, 2026 at 01:43AM

Show HN: Visualization of Top News Stories https://bit.ly/3UMLn8H

Show HN: Visualization of Top News Stories news stories has bigger headings based on updates/votes. you can also add/remove the sources and save a unique link https://bit.ly/4yKXlh8 October 25, 2026 at 11:10PM

Show HN: AI Heat Map Sourced from over 140 News Feeds https://bit.ly/4i2R5MB

Show HN: AI Heat Map Sourced from over 140 News Feeds https://bit.ly/4z1zcDQ October 25, 2026 at 04:25AM

Show HN: Redmi phone can do things that $16K GPU is needed for on Ethereum https://bit.ly/4jKgV9v

Show HN: Redmi phone can do things that $16K GPU is needed for on Ethereum Recursive State proof verification from genesis: 10.78 seconds Peak process memory: 192.2 MiB Subsequent block downloads and verification: 11.94–13.20 seconds https://bit.ly/4spM5VU October 25, 2026 at 12:32AM

Show HN: Call4me – a ChatGPT plugin that lets it make phone calls on your behalf https://bit.ly/4jF1EGU

Show HN: Call4me – a ChatGPT plugin that lets it make phone calls on your behalf https://bit.ly/47DC2mC October 24, 2026 at 11:00PM

Show HN: How religions evolved? Charts, Maps, Citations https://bit.ly/4zhtldJ

Show HN: How religions evolved? Charts, Maps, Citations https://bit.ly/4z9scF6 October 24, 2026 at 08:37AM

Show HN: Encarta 95 Web https://bit.ly/4dQNcIc

Show HN: Encarta 95 Web Encarta is super nostalgic, and I was surprised it wasn't available to use online. So I embarked on the difficult task of making it so. The way this works is the most convoluted, nonsense and brittle system ever... but it works as a statically hosted gh-pages site! Please note: All the material on this site is freely available through the internet archive (see github readme) Github repo -> https://bit.ly/4zSjDyp https://bit.ly/4BqtOfa October 24, 2026 at 08:18AM

Show HN: Inference Cooperative, user-governed AI https://bit.ly/4yDCZpM

Show HN: Inference Cooperative, user-governed AI https://bit.ly/4yIF8k1 October 24, 2026 at 04:32AM

Show HN: libfpv - Modding FPV Drone into Any Game https://bit.ly/4zInT3s

Show HN: libfpv - Modding FPV Drone into Any Game https://bit.ly/4i2gqGv October 23, 2026 at 10:26PM

Show HN: Impossible Machines: declaratively program the physical world https://bit.ly/4yW6iEx

Show HN: 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! https://bit.ly/489UfIx October 23, 2026 at 12:54AM

Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI https://bit.ly/4sgHi8Y

Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI Hey HN, we recently open sourced our Consumer Agent Testing Tool to help teams iterate against proprietary assistants like Muse and Instinct. We built this to reduce our own frustrations with building an MCP/API for these agents to consume. The problem: testing against these tools is hard! Agent memory + account statefulness make reproducibility, in the ways required for repeatable/reliable outcomes, between agents and the APIs/MCPs they interact with very challenging. The solution: CATT lets devs test their services against a surrogate Muse or Instinct agent (not affiliated with either of these companies). Testers define starting conditions, approvals, and success conditions for their service's state. CATT then records the full interaction (incl. tool calls, responses) so it can diff what happened from what the agent reports. Runs can be tested in local builds or via CI, with or without LLM backing. CATT is designed to emulate the important parts of personal assistant interactions. Its got: - Tool calls and command-line tool access - Simulated approvals for service actions - Outcomes tracking and comparison - Optional MCP profile based on an unofficial Muse template There are limitations to how much we know about different assistant specific behaviors so the tool labels its assumptions as `documented`, `unofficial`, `assumed` or `unknown` for developer review. We'll do our best to keep the tool updated as new insights about the internal workings of these assistants come to light. It is an area of active research and interest, a good example is this recent report on how Instinct uses Exa for web search [0]. Are you building a connector or MCP? If yes, we'd like to hear from you! Have you had assistants behave incoherently, use stale information, or procalim success without evidence? What else should we add tests for? The best way to get started is...to point your coding assistant at the repo and ask it to integrate the tool with your CI or local testing pipeline! Hope it's helpful! [0]: https://bit.ly/4ic9xB1... https://bit.ly/4i9kSSt October 22, 2026 at 11:18PM

Show HN: Embodsi – Embodied Super Intelligence https://bit.ly/3UKmCKh

Show HN: Embodsi – Embodied Super Intelligence embodsi is a generative AI MMO experience that runs in the browser. It allows people to communicate (text, audio, video, avatar emotes and movement) and collaboratively build 3D spaces and games via LLMs connected to harnesses and sandboxes for object modeling, space layout, game logic, and driving persistent avatars with shared context and memory. It’s different from existing 3D social apps (AFAIK) because it enables people to build multiplayer virtual worlds, games, and characters with generative AI right from their browser (desktop, mobile, or VR), in nearly infinitely-extendable recursively tiled interconnected spaces, while allowing people to interact in a public commons or easily create a private channel to enjoy the same spaces with their chosen friends and community. The brief backstory is I was running my personal “pelican benchmark” [1] on GPT-6 Astra, which when I ran on Gemini 3 Pro last November couldn’t even put heads on 3D models the right side up [2], and was astounded by the initial results. I gained inspiration for an art project and social experiment that was going to have nine interconnected, benevolent virtual worlds that people could explore and hang out in with AI characters, but by the time Opus 5.5 was released I was gaining so much momentum and having so many ideas and so much fun building I just kept building more and more with the constraint of minimizing MVP scope lifted by agentic coding. I let the project become an ever-evolving wishlist of capabilities for a more interesting social environment as I became increasingly fascinated with the prospect of embodying creative machine intelligence in 3D space with people, realizing that rather than just limiting to building the spaces and characters I imagined I might enable people to co-create endless spaces and characters in a shared world. There’s so much to do still but I’m sharing now even if it feels a little too soon (this is the first public announcement of embodsi’s existence) because I think it’s better to build in the open so people might guide the development and help it evolve in a good direction as model capability improves at a jaw-dropping pace. For people that have the budget to build I hope to see you in embodsi creating amazing things! And for everyone regardless of means (I’ve tried to keep as much free and accessible as financially feasible) I hope you meet amazing people, discover awesome spaces, and enjoy your time in embodsi :) I’ll be around here and embodsi to answer any questions! Thanks for your feedback and critique. - Laser P.S. SI != AI — but an emergent property of many people and what we create cascading and recursively interacting [3] [1] https://bit.ly/4eLrIwx [2] https://bit.ly/4ib8CRk [3] https://bit.ly/4yt30rP https://bit.ly/4zHrMW9 October 22, 2026 at 12:15AM

Show HN: I built a Markdown and raw HTML blog platform scoring 99 on PageSpeed https://bit.ly/3UfzeZI

Show HN: I built a Markdown and raw HTML blog platform scoring 99 on PageSpeed Hello. I built a blogging platform on my own over two years. I like running my blog, but I couldn't find a blogging platform I really liked. First. I thought a blog had to be really lightweight. Fortunately, after a lot of effort, I was able to achieve satisfactory results. (99 to 100 score) Here is a sample blog: https://bit.ly/4ia4nph You can check it with PageSpeed Insights: https://bit.ly/4dQurVh... SEO score of the sample blog is low because I blocked it from search engine indexing (noindex). Second. I think bloggers should have control over their own blog. The blogging platforms I used had several problems. Unnecessary JavaScript chunks. Ads that the platform inserted into my blog, not my own ads. Cannot manage multiple blogs. An editor that makes it hard to write semantic markup. Limited customization options. I was dissatisfied with the difficulty of placing my own ads. And to solve this, I spent quite a long time researching and developing it on my own, and finally created it. I'm glad to share this launch with HN. I would appreciate any criticism, feedback, and interest. https://bit.ly/3UfrlTU October 22, 2026 at 12:41AM

Show HN: ZeGrapher v4: modern math plotter https://bit.ly/3W1vn2W

Show HN: ZeGrapher v4: modern math plotter ZeGrapher is a free an open-source math plotter, first release in 2011 (I thought there were no such app on Linux at the time), that I kept sporadically updating ever since. Last version was 6 years ago but a lot of work went into it. v4 is a near complete rewrite to a modern interface and approach, inspired by desmos. Interesting differenciating features: - Computing and plotting recursive sequences - svg and pdf export at the physical size you see or set on your screen, in centimeters - "schrodinger" constants: define constants that take many values at once, any expression that depends on it is plotted for each value, with a user set color gradient. - an interesting graphical way to deal with CSVs and can handle large ones (millions of lines) The rest on the website ! I want it to be able to make graphs that can be used in research articles, not quite there yet. I want math formatted (like katex) titles and legends at least. Already found stuff to fix on this rc, feedback welcome! https://bit.ly/4ekttAI October 22, 2026 at 12:22AM

Show HN: SimCity, but with Permits https://bit.ly/4sfrJi3

Show HN: SimCity, but with Permits https://bit.ly/4shrbrJ October 20, 2026 at 07:29PM

Show HN: Dovepass – can I legally fly a drone along this exact path in SF? https://bit.ly/3U7I0J2

Show HN: Dovepass – can I legally fly a drone along this exact path in SF? Dovepass answers one question for drone operators: given two points, can a drone legally fly between the two points? I build route planning for delivery drivers and wanted to check what it would look like if the vehicle flies. Drone navigation is different from land-based vehicle navigation. In addition to road and traffic data, it requires data on buildings, building height, wind speed and direction, and total load, including the payload a drone might carry. It is also governed by a set of rules; depending on the area, federal, state, or county rules may apply. The decision point becomes whether, at each point on the route the drone can fly based upon whether regulations permit, the wind direction favours it and whether it flying over a road or people? Depending on when the drone flies, the same path valid two hours ago may no longer be valid. For example a trip from 24th & Valencia ( Mission) to 19th Ave & Irving (Inner Sunset) and back is 5.1 km each way. A DJI mini 4 Pro would take 19 min on 7 mph winds from the west and use 92% of its usable battery and give a Go signal with warning. But at 11mph wind from the same direction would become No-Go because it would use 111% of its usable battery. Or whenever there is a Giants game at Oracle Park, this route is unusable because it is 2.5miles from the stadium. FAA bars all drones within 3 nautical miles from a stadium from 1 hour before the game to one hour after it ends. I chose San Francisco as the first city to build this because there is enough data about the buildings (92% coverage), wind data is easily available at the drone flying height, and the city has a mix of slopes, water bodies, buildings and airport-related airspace restrictions all in one city. The city also has local rules regarding drone flights in parks - both operated by the city as well as by Golden Gate National recreational areas ( National Park Service). I used kimi to build it and claude acted a sa judge. To understand more about the challenges faced during the build and the tradeoffs made please read - https://bit.ly/3VXkC1F " https://bit.ly/4eldB0O October 19, 2026 at 08:21PM

Show HN: Chai-UI – A design system to generative AI apps https://bit.ly/4yzHx0u

Show HN: Chai-UI – A design system to generative AI apps https://bit.ly/4BhxDDa October 20, 2026 at 01:06AM

Show HN: Hybro – an open interoperability engine for AI agents https://bit.ly/4yXPmyc

Show HN: Hybro – an open interoperability engine for AI agents I built an open interoperability engine for AI agents. Connect your favorite agents and harnesses. Work together. Appreciate for any feedback. https://bit.ly/4yVMEcd October 19, 2026 at 12:41AM

Show HN: InfiniDomino – practically infinite world of dominoes to knock over https://bit.ly/4savjK6

Show HN: InfiniDomino – practically infinite world of dominoes to knock over Was thinking of other “infinite” type games I could make after making infiniword and thought of how fun it is to watch dominoes fall over. https://bit.ly/4yxtusu October 19, 2026 at 12:33AM

Show HN: 500 clocks in one 6.3 MB HTML file by Opus 5.5 https://bit.ly/3U66Mcx

Show HN: 500 clocks in one 6.3 MB HTML file by Opus 5.5 Lately I've been testing frontier models by having them create self-contained web pages that display clocks--sort of my personal version of Simon Willison’s pelican-on-a-bicycle metric. I have been particularly impressed by the variety, interest, and quality of the clocks created by Claude Opus 5.5. Over the course of several sessions in the Claude chat interface, I had it build a total of 500 clocks. Claude’s summary of the prompting process and page design is here: https://bit.ly/3U4rKss https://bit.ly/4jxNmrD October 18, 2026 at 05:04AM