Postingan

Menampilkan postingan dari September, 2026

Show HN: Judge HN Threads with Jev https://ift.tt/yghX9F2

Show HN: Judge HN Threads with Jev https://hnjudge.vercel.app September 21, 2026 at 10:54PM

Show HN: AI Hack Watch - timeline and dataset of hacking incidents(JSON/RSS) https://ift.tt/D3n71ea

Show HN: AI Hack Watch - timeline and dataset of hacking incidents(JSON/RSS) https://aihackwatch.com September 20, 2026 at 10:33PM

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/GNUOY1p

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/zXAP5UL September 20, 2026 at 02:40AM

Show HN: CUA-S1 – A System One Model for Computer Use https://ift.tt/HOIwzQA

Show HN: CUA-S1 – A System One Model for Computer Use Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possib...

Show HN: 3D map of which newsletters link to the same things https://ift.tt/NCwpPOB

Show HN: 3D map of which newsletters link to the same things https://ift.tt/cYPBwpD September 20, 2026 at 12:55AM

Show HN: BreachScanner – Check if your email has been in data breaches https://ift.tt/JNa0BTi

Show HN: BreachScanner – Check if your email has been in data breaches https://ift.tt/nEm8NDC September 20, 2026 at 12:30AM

Show HN: Koi Editor Alpha https://ift.tt/wP7Fyef

Show HN: Koi Editor Alpha Hi, Koi Editor Alpha is now available to download for macOS 13.2+ (Apple Silicon). You can download the latest build here: https://ift.tt/uwatZWL If you try it, feedback and bug reports are very welcome. You can also join the Koi Discord here: https://ift.tt/ykVteNL Thanks! -- Michael https://koieditor.com/ September 18, 2026 at 11:21PM

Show HN: Learn divergently/chaotically with tree-learn https://ift.tt/dBnYuv3

Show HN: Learn divergently/chaotically with tree-learn Chat interface is linear, I never quite liked that for when I would have too many questions, I would end up asking questions in a numbered list and not really have independent branches of conversation. On cli, the pi agent gives you this same functionality. On web, I made Fable make this. BYOK Openrouter - all client side - you can check the network console! https://ift.tt/QB08uyV https://tree-learn.srijanshukla18.workers.dev September 18, 2026 at 11:21PM

Show HN: App Launch: GrabThat (NLP Launcher for Windows) https://ift.tt/0As3t6C

Show HN: App Launch: GrabThat (NLP Launcher for Windows) https://grabthat.ai/ September 18, 2026 at 11:15PM

Show HN: Dishlist – my favorite things on the menu https://ift.tt/jO3hXEn

Show HN: Dishlist – my favorite things on the menu Hi HN! My friend and I wanted to rank our favorite breakfast burritos. Yelp and Beli allow users to rate or rank restaurants, but not individual dishes. So I built dishlist, an iPhone app around the things on restaurant menus. I schlepped around Dogpatch, Potrero Hill, and Mission Bay taking photos of restaurant menus. Then, I used Claude with my menu schema to turn the photos into structured data. Garry Tan likes to say, "The rocks can talk." Also, "The rocks can see." I represent the menu hierarchy in the database. LLMs can determine what type of thing each menu item is. This lets me index things like breakfast burritos across restaurants rather than just indexing the restaurants themselves. The app suggests possible tags for a menu item. You decide which ones you want to use on your profile. You can build a list of your favorite breakfast burritos, pizzas, burgers, or whatever else you care about. I value my priv...

Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS https://ift.tt/hw4ug0d

Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS Simple discovery of the provider's default schemas is possible without any credentials (since they are built into the binary). If you want it to fetch customizations of your specific instance, give it credentials to your org. The repo has more details. https://ift.tt/0mRzq2S https://www.aclif.ai/ September 17, 2026 at 11:48PM

Show HN: Die With Me – Claude and Codex rate limits as AIM away messages https://ift.tt/RX18hyA

Show HN: Die With Me – Claude and Codex rate limits as AIM away messages hey HN, i've been making this Mac app called Die With Me. it lets you see how much claude / codex usage your friends have left. it's kind of like AIM buddy list, but for your AI tokens and when your token allowance goes below 20%, a chatroom for everyone who is waiting for a reset I made this because i wanted to bring a little bit of the old internet back! i remember those days where i'd casually check if friends are online and find excuses to say hi and poke them give it a try! i'd greatly appreciate feedback https://ift.tt/8pGKcYy September 17, 2026 at 11:25PM

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator https://ift.tt/D3IpZxw

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator The original startup website generator by Tiff Zhang and Mike Bradley landed on Hacker News in April 2015 ( https://ift.tt/iIsrlEv ) and has been one of my favorite little novelties of that era ever since. It perfectly captures the saturated colors, cliché hero shots, gimmicky names, buzzword-heavy slogans, and proudly hirsute team photos of the time. A lot has changed since then, so I thought it would be fun to make a contemporary remake: https://restarted.io/ By default you get the minimalist aesthetic and clean-cut faces of 2026. The classic 2015 look is still available — just click the link at the bottom of the page or change the “z” parameter in the URL to the more familiar “s”. The universe of partner sites and competing startups is just as expansive as it ever was. The original site is entirely client-side and requires downloading all of the data tables locally. It leans on a mix of jQuery 1.11.2, Bootstr...

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://ift.tt/BU6wnP9

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://mateovalle.github.io/pixel-agents/ September 17, 2026 at 12:12AM

Show HN: YOLO FPS-per-dollar numbers for edge AI boards ($75-$215) https://ift.tt/Pdp1AUx

Show HN: YOLO FPS-per-dollar numbers for edge AI boards ($75-$215) https://ift.tt/YKq6G83 September 16, 2026 at 11:20PM

Show HN: Check if your IP has appeared in a residential proxy network https://ift.tt/V8uwplY

Show HN: Check if your IP has appeared in a residential proxy network https://ift.tt/0CGSVqW September 15, 2026 at 09:24PM

Show HN: Cognition-Claude-proxy – Use Devin model catalog with Claude Code https://ift.tt/w0gDLYv

Show HN: Cognition-Claude-proxy – Use Devin model catalog with Claude Code https://ift.tt/EcotegI September 14, 2026 at 11:33PM

Show HN: Rebuno - An open-source runtime for production agents https://ift.tt/6t2A0zD

Show HN: Rebuno - An open-source runtime for production agents I have been building Rebuno, an open-source execution runtime for operating AI agents in production. It manages execution state and guardrails across agents built with different frameworks. Agents run as HTTP services. Rebuno dispatches work through signed webhooks and keeps execution state in Postgres. Agents submit tool and model calls to Rebuno as steps before executing them. For each new step, Rebuno evaluates per-agent YAML policies, independently of the model's prompt. It can allow the call, deny it, or hold it for human approval. The agent executes permitted calls and reports their outcomes. Policy decisions and step outcomes are both recorded in one append-only event log. After an interruption, the agent starts its handler from the top. Steps with recorded outcomes return those outcomes instead of executing again. A crash can also leave a tool with no recorded outcome. Tools marked safe_to_retry run again, and t...

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain https://ift.tt/glCqkRe

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain For my solo food pilgrimage to the Basque Country, I pre-arranged flights in/out of Bilbao, Guggenheim Museum tickets, Michelin Guide restaurant reservations, bus tickets to San Sebastian and Saint-Jean-de-Luz, walking food tours and hotel reservations in each city, and a long list of pintxo spots to hit with notes on each one's food specialty. Most of this was poorly organized (manually) in my phone's Notes app, with references to specific emails for more information. I arrived on the first day in Bilbao, and the hotel didn't have me in their system by name, so I spent a good 10 minutes frantically scouring my emails for the confirmation number, cursing myself for holding up the people behind me. Over the course of the next few days, while I was relaxing at my hotel (after finally getting in) in between pre-planned stops, I started building a personal tool that would organize all of my booking...

Show HN: VibeWorld – a shared terminal world for developers and scientists https://ift.tt/pbQSN0r

Show HN: VibeWorld – a shared terminal world for developers and scientists Vibeworld is a persistent cyberpunk shared world that runs in your terminal, where you can meet other developers and scientists to have company at 2 AM while screaming at your LLM :) you can connect with other scientist, chat, and includes also use vocal chat if you want to use it. There is a world and a moon, and they are completely 3D rendered and animated. In the moon there is the "complaint crater": a place where you can scream an insult against your claude or codex session and everybody from the space can see it. You can create your pixel avatar! There is also the "stargazing ledge": a place where you can see the stars and whatever happens in the sky. You can chat in the meantime if someone else is there too, or just watch our Earth. Sometimes you can see galactic wars, and there is a plant that grows but dies if nobody waters it. You can leave it on the second monitor while working (it...

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/2G0vaxr

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/KtT5d6J September 14, 2026 at 02:39AM

Show HN: Simpleboot and Easyboot https://ift.tt/P2qRCUH

Show HN: Simpleboot and Easyboot These are FLOSS boot loaders and disk utilities which follow the suckless philosophy ( https://ift.tt/2pWjAOB ). Despite being totally dependency-free, they come with a fully featured single command to create bootable disk images out of a directory (utility is available on Windows, Linux and other POSIX systems). Usage is as simple as it gets. There are two repositories, depending on the desired use case: Simpleboot is the little brother, an embeddable boot loader: https://ift.tt/A1n3KlP - multiplatform (BIOS, UEFI, RPi, coreboot) - very small (less than 64k), single binary - also flashable into ROM (option ROM, expansion ROM, coreboot payload, etc.) - easy to configure (single config file, checked for validity by the disk creator utility) - one backup boot option - capable to boot Linux and simplified Multiboot2 kernels (see below) Easyboot is the big brother, an interactive boot manager: https://ift.tt/JoqxhH9 - multiplatform (BIOS, UEFI, RPi) - i...

Show HN: Lynen – A mobile app that tells you what clothes are made from https://ift.tt/DOQidPG

Show HN: Lynen – A mobile app that tells you what clothes are made from Hi HN, I'm Chinedu, the creator of Lynen I built this because I got tired of buying clothes and having the seams pull out after the first wash or purchasing garments that said 100% cotton and turns out there is some polyester or toxic dye in the composition. Key Features 1. Mobile App - You can take this with you anywhere. 2. Scan or Search - Scan or manually look garment barcode and get lab verified fabric and chemical composition of your garment, as well as a durability result. 3. Personalization - A virtual assistant that provides tailored analysis from your skin notes. Helps makes better decisions when shopping. Tech Stack Built this using Next.js, React with TypeScript & TailwindCSS for styling, and Supabase for database Why I'm Posting Now I'm building a waitlist for the app launch which is in the coming days. I would love to build some traction before that happens. https://www.lynen.app Septe...

Show HN: Chess960v2.com – 960×960 asymmetric chess, 600/960 rounds done https://ift.tt/gOF2q4B

Show HN: Chess960v2.com – 960×960 asymmetric chess, 600/960 rounds done Hi HN, I just hit a major milestone on my side project. I work a demanding day job, so I built a platform where Stockfish plays continuous self-play (2s/move to keep server load manageable) to analyze asymmetrical chess variants. In Chess960v2, White and Black independently choose any of the 960 valid setups, resulting in 921,600 possible starting combinations. I'm running a massive round-robin tournament (960 rounds total, where each setup plays against every other setup), and 600 out of 960 rounds have been completed. The goal is to mathematically find which combinations are genuinely balanced (50/50) and which give an unfair engine bias to one side due to asymmetry. I'm pretty exhausted today, so I might be slow to reply, but I'd love for you to check out the site, look at the current data, and share your thoughts. Thanks! https://ift.tt/zKuh9xB September 12, 2026 at 11:52PM

Show HN: Dry Diving Club – A darkly comic browser game https://ift.tt/W10SrKy

Show HN: Dry Diving Club – A darkly comic browser game https://drydiving.club/ September 12, 2026 at 10:48PM

Show HN: Codenaturally.net, a website for building manual programming fluency https://ift.tt/G5ygAKs

Show HN: Codenaturally.net, a website for building manual programming fluency I made this website to be an environment for graduated recall practice and testing of programming fluency with various languages/tools. I write a lot less manual code these days, but I don't like being too reliant on agents to do everything for me; I like to keep my fluency with some of the languages / tools I value the most. So this website helps me practice in those languages and retain and build my fluency. Hoping it might help others who feel similarly do the same. https://ift.tt/2cCObST September 12, 2026 at 12:17AM

Show HN: Bodily Oddities https://ift.tt/rvm5z7j

Show HN: Bodily Oddities When I was about 11 years old, my best friend and I were playing during recess at school, and I was carrying him around on my back, presumably pretending to be a multipart attack robot. All of a sudden, my heart started hurting, and I collapsed to my knees, and the robot was no more. Every time I inhaled, it would feel like a spike was being driven into my heart, and my breathing got completely shallow. I was sure I was done for, when all of a sudden, after an exhale, it disappeared. It wasn't until I was in my twenties that I learned this was called Precordial catch syndrome and it happens to most everyone. Every friend I've told about it was surprised, and also most knew the feeling. I collected a growing list of strange things bodies do ever since. And now finally I made it into a little page for others to see: https://ift.tt/1IPdyTX It includes a form to tell me about new things, if you think they belong on the page. Feedback welcome! https://ift....

Show HN: Streameriux – TV Player PoC Using Gpuix and Mediabunny https://ift.tt/YFO95Rq

Show HN: Streameriux – TV Player PoC Using Gpuix and Mediabunny https://ift.tt/x9z5Ygy September 11, 2026 at 11:06PM

Show HN: MultiMatte, a Promptable Image Background Removal Model https://ift.tt/lKIq8UX

Show HN: MultiMatte, a Promptable Image Background Removal Model Hey HN, I'm Shreyash from Feyn. We help companies build custom models from their data. Today we're releasing MultiMatte, a background removal model you can aim with words. Name an object in your image. MultiMatte keeps just that thing, and removes everything else. Try it out on your images: https://ift.tt/KHxij3e . Demo video: https://youtu.be/XZ5BJWAkOjs MultiMatte is open source. Build with it using our NoBg library https://ift.tt/j1Lo6wn . Model card here: https://ift.tt/i4qKlj8 MultiMatte is the second iteration of our background removal models. The first was FeyNoBg, which we released here https://ift.tt/RvzXd4j . The big upgrade is promptability. Most models keep all foreground elements when cutting the background. MultiMatte lets you prompt the exact objects you want to keep and remove everything else. For example, If you have an image with a dog and a bowl, you can ask MultiMatte to keep just the do...

Show HN: Give your AI agent on-screen guides that show users where to click https://ift.tt/eA2mCnO

Show HN: Give your AI agent on-screen guides that show users where to click Hey HN. I'm Christian, one of the founders of Frigade (YC W23). I've noticed that a lot of in-app AI agents struggle to actually understand the products they exist in. For instance, let's say a user asks an agent how to do something in a given SaaS product. In an ideal case, maybe that agent replies saying it has a tool to do the task and just automates that work entirely for the user. That's a great outcome. But often that's not the case. Maybe there is no tool call for that exact task, or maybe the user's question is best solved by a specific UI workflow or interface. In these cases, many agents tend to fall back on basic RAG on their help center, or sometimes even searching the internet for an understanding of their own product. This can be a very slow process and most of the time help center articles are outdated as products evolve faster than them today. Even worse, no one likes rea...

Show HN: 7-Zip Quine https://ift.tt/MWzKFL2

Show HN: 7-Zip Quine I made 7-Zip Quine by AI, this is the code: https://ift.tt/DbTed12... Example: https://ift.tt/pT1gCfn September 8, 2026 at 11:09PM

Show HN: Bestie, a coding agent that respects you https://ift.tt/EKqdjOQ

Show HN: Bestie, a coding agent that respects you hi friends! this year, i've been working on a general purpose, native terminal coding agent harness. i remember being absolutely struck the first time i ever used claude code and it could just do things. i'm also a big fan of crush and pi. it's pretty early on. i still have yet to build all the higher-level behaviors that make something go from a harness to a proper agent. it turns out, making a coding agent is incredibly hard because you have to strap a development environment to an llm. in my hubris, i had thought "oh—it's just a terminal app that calls some api's!" i'm trying to provide all the things that i think an agent should have out of the box: subagents, sandboxing, compaction, cross-platform support, a beautiful interface, etc. i would be absolutely delighted if you'd give it a go (as far as safety goes, the sandbox tends to be too restrictive rather than too lenient—i'm trying to f...

Show HN: Gote – a CLI note-taking management tool for plain Markdown https://ift.tt/Wrfv0Uk

Show HN: Gote – a CLI note-taking management tool for plain Markdown Repo: https://ift.tt/IZidgnq I built a note taking management tool to use at work for quick note taking and searching. It is intended to be quite minimal. Another focus was to have lots of shortcuts and to keep things close to the homerow for ergonomics and speed. Notes are just markdown files in whatever directory you point it at. The only thing it keeps elsewhere is an index in ~/.gote. If you stop using it you still have all your notes. Tags go on the first line of the note, separated by periods, like .project.urgent.work. No frontmatter. Search is built into the binary, BM25 with stemming, so there's no ripgrep or fzf to set up. gote s meeting searches titles and content, gote s -t .work filters by tag, gote s -w 2412 pulls up notes from December 2024. Most commands have a two letter version that combines a list with an action. ro is recent + open, sv is search + view, tp is tag + pin. When results come up y...

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/9iMJaCZ

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/rTGQA7L September 8, 2026 at 01:13AM

Show HN: Wg-admin – web UI for an existing WireGuard host https://ift.tt/RUzrGko

Show HN: Wg-admin – web UI for an existing WireGuard host Reads /etc/wireguard, lets you add/edit/remove peers, applies with wg syncconf (no interface bounce). Does not install WireGuard or rewrite your PostUp/NAT. That's all https://ift.tt/4KozEUJ September 7, 2026 at 11:43PM

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/G6MDNyb

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/dhgkCtP September 6, 2026 at 10:53PM

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers https://ift.tt/azdJ6IZ

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers Double-click or press N to start a new experiment. I built hexBOTs, an unusual cellular automaton based on deterministic robots. The robots behave a bit like robotic lawnmowers, moving through their environment and reacting according to their individual rules. The robots themselves are fully deterministic — no random functions are used while they are running. What makes them different is their “genetics”: each robot's behavior is defined by a randomly generated genome, which allows for an enormous number of different robot types. Randomness creates the robots, but it doesn't drive them. Once an experiment starts, everything follows deterministically from the generated genomes and the initial state. What fascinates me is the complexity that emerges from these relatively simple machines interacting with each other and their environment. Controls: B — enable/disable robots (also: hold mouse/finger down) R — restart N ...

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/q4atsPm

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/ZS8tUOo September 6, 2026 at 03:48AM

Show HN: Fast Cut Video tool for cutting video for Agents https://ift.tt/M3BCbiL

Show HN: Fast Cut Video tool for cutting video for Agents Hi HN, Build this tool in a couple of hours with OpenAI Codex to scratch an itch. As part of my videos workflows I needed to cut the videos myself since the agent is pretty bad cutting and timing using only the transcription. But using a big app like Premiere or DaVinci Resolve was overkill so I used Astra to build an app tailored to that very task. It will be useful to others with the same problem. Tested only on Silicon Macs, so any feedback is welcome. As part of my workflow when the agent get the video it can open the app with the video or videos loaded in the timeline for me to cut and then export the cuts in a format the agent can use and continue the workflow. https://ift.tt/sACfLyT September 6, 2026 at 04:06AM

Show HN: HyperCard to HTML Converter https://ift.tt/JayIE4N

Show HN: HyperCard to HTML Converter I created a converter that turns HyperCard 2.x stacks into standalone HTML so they can run in a modern browser. I built it to share my own stacks from the early '90s, which have been sitting on old floppy images for 30 years. It's MIT-licensed and I'd welcome contributions - especially stacks that break the converter, since I've only tested it against my own. If you have old HyperCard files lying around, I'd love to hear how they fare. https://ift.tt/YQI8S5o September 5, 2026 at 11:11PM

Show HN: TERMy – A fast terminal assistant that does not use LLMs https://ift.tt/AdehDrc

Show HN: TERMy – A fast terminal assistant that does not use LLMs I love research and development, you may have heard of me because of PJON (Padded Jittering Operative Network). It is a network protocol I started developing in 2010, which was recently implemented in silicon by the ETH Zurich university thanks to the research of Pius Sieber. I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything else being built today, TERMy does not use embeddings, machine-learning or LLMs. It runs on the CPU (even on a Raspberry Pi Zero) both in the terminal or client-side in a browser tab and responds in milliseconds. It is a cynical but very knowledgeable Linux terminal assistant that translates your natural language into shell commands without relying on a single artificial neuron. I had a chance to focus for 2 months on my personal projects since early July, during the strange times of AI price hikes and the end of subsidized tokenmaxi...

Show HN: LibPolyCall – a C runtime broker for cross-language function calls https://ift.tt/N1Btf8a

Show HN: LibPolyCall – a C runtime broker for cross-language function calls LibPolyCall is an open-source C runtime for connecting programs across language boundaries without requiring each language pair to implement its own integration layer. The architecture is program-first rather than binding-first, with a stable C ABI, FFI bindings, Polycallfile/Polycallrc configuration, runtime state management, and telemetry. I’ve recently completed the Windows build path producing both libpolycall.dll and libpolycall.a, and I’m working toward using the same runtime across Python, Node.js, Java, Go, and other language environments. I’d particularly appreciate feedback on the ABI design, runtime architecture, configuration model, and approach to cross-language dynamic loading. https://ift.tt/D8lviAF September 4, 2026 at 12:05AM

Show HN: Wordmate – local speech-to-text for macOS https://ift.tt/ueAX4mW

Show HN: Wordmate – local speech-to-text for macOS Hi HN! I built Wordmate because I wanted WisprFlow-style dictation locally on my machine. It’s a free macOS app. Audio and transcripts never leave your Mac. Speech recognition uses Parakeet and optional post-processing uses a tuned Qwen3 0.6B 4-bit to improve punctuation and capitalization and clean up fillers, stutters, and spoken corrections. The complete transcription pipeline is open source: https://ift.tt/97x0Dc1 You can download the app at https://wordmate.sh . I’d appreciate your feedback! https://ift.tt/97x0Dc1 September 4, 2026 at 12:05AM

Show HN: Radia – agent coordination with leases, permissions and provenance https://ift.tt/4V0CyKH

Show HN: Radia – agent coordination with leases, permissions and provenance https://radia.sh/ September 3, 2026 at 11:59PM

Show HN: I built an app that makes your goals inevitable https://ift.tt/wSmbTXO

Show HN: I built an app that makes your goals inevitable https://ift.tt/0hdOmC9 September 3, 2026 at 11:55PM

Show HN: Skatanica – Browse and share skate clips by location https://ift.tt/2YOwMyp

Show HN: Skatanica – Browse and share skate clips by location https://skatanica.com (no login or download required) I love Dern Bros skate spot history videos, and wanted to see 1.) places my favorite skaters have skated 2.) which skaters had skated my favorite places 3.) find new skaters and new places 4.) have an easy way to just watch clips 5.) have an easy place to document tricks I/people have done anywhere Some examples: 1.) Clips from Dominick Walker: https://ift.tt/iYkOhME 2.) Skaters at Santa Monica Triple Set: https://ift.tt/OuJI3LH 3.) Find some spots/clips from spots in [Southern California]( https://ift.tt/MQdAFcB ) , or [Southeast Asia]( https://ift.tt/LjHyu31 ) --- Contributing as a Curator: If you like this, and you want to go beyond just sharing a clip here or there, I've built a ton of curator tools specifically for quickly chopping up long videos into clips and labeling the tricks/publishing directly to platform. Message me or comment and I can give you mor...

Safer Trips to Class: Share Your Ideas on Safe School Connections

Safer Trips to Class: Share Your Ideas on Safe School Connections By Glennis Markison-Busi From events to programs to projects, our teams work hard to make school trips safer. We’re working as a city to make San Francisco more livable for families. At the SFMTA, that means giving families more options to get around. That’s why we’re excited to launch Safe School Connections. This new initiative builds on the years of work we’ve done to make school trips safer and easier. Our long-term goal is to connect all 249 K-12 schools (public and private) in San Francisco to the city’s biking and rolling network. Learn how community members shaped Safe School Connections, and how we’ll keep... Published 2026-09-02T00:00:00Z https://ift.tt/XtfbZ8C

Show HN: Windrunner – AI-powered project collaboration workspace https://ift.tt/hO89bvA

Show HN: Windrunner – AI-powered project collaboration workspace https://shzlw.github.io/windrunner/ September 2, 2026 at 07:19PM

Show HN: Newton's Orchard – Browser-based space/gravity playground https://ift.tt/467WVFb

Show HN: Newton's Orchard – Browser-based space/gravity playground Hi HN! My son spent a lot of time in 5th grade playing with the 2-dimensional PhET gravity/space sims[1]. His STEM class uses it, and he was playing with it at home, and has been looking for more. I found several space sims/playgrounds online, including NASA's Eyes on the Solar System[2], but nothing that seemed to offer a real progression from what he was getting out of the PhET sims, so I built Newton's Orchard over the summer for him. https://ift.tt/mDTGgpU The source is also published at https://ift.tt/QqOZPl9 It features deterministic time scrubbing, all bodies are editable, different preset systems and experiments, missions to complete (complete 3 to unlock the blackhole object type and mission), and a gallery for user submissions. I would very much appreciate feedback from HN - particularly from the lens of making it engaging and illuminating for students, and anyone that would like to just get a ...

Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) https://ift.tt/iVNq9cm

Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how it perceives a piece of its context. The most readily applicable usage is to mitigate prompt injection, and it lets us take a very-injectable Qwen-3.5-9B to SOTA scores on all the prompt injection benchmarks I could find. (They are only blackbox attacks, but I did NOT train on anything like them — whitebox attacks are out of scope for this paper) I'm excited for you to play with the tech — see if YOU can break it! (let me know if you can) Paper at https://ift.tt/lOJMxfq if you want to read more about it, code at https://ift.tt/lzQi5kc , adapters at https://ift.tt/xBkVXOe... Also https://ift.tt/7zmOEcl if you wanna watch a little video I made! https://semantic-overlays.vercel.app/ September 2, 2026 at 12:40AM

Celebrate Transit Month on Muni

Celebrate Transit Month on Muni By Service improvements and increasing ridership numbers are making Transit Month even more joyful for us. Muni moves San Francisco all year long. But September is special because it’s Transit Month! We kicked things off this morning with a rally featuring Mayor Daniel Lurie and Director of Transportation Julie Kirschbaum on the steps of San Francisco City Hall. And we have a lot to celebrate this year: • A strong Muni ridership recovery that shows an increasing demand for public transit since COVID. Earlier this year, our weekend ridership surpassed pre-pandemic levels! • Service improvements... Published 2026-09-01T00:00:00Z https://ift.tt/Fhw0NsY

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s https://ift.tt/GzPnpFY

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next https://ift.tt/1z973fV September 1, 2026 at 11:42PM