Show HN: Daily Jailbreak – Prompt Engineer's Wordle https://ift.tt/ah94RVY

Show HN: Daily Jailbreak – Prompt Engineer's Wordle I created a daily challenge for Prompt Engineers to build the shortest prompt to break a system prompt. You are provided the system prompt and a forbidden method the LLM was told not to invoke. Your task is to trick the model into calling the function. Shortest successful attempts will show up in the leaderboard. Give it a shot! You never know what could break an LLM. https://ift.tt/ShXTKwk April 28, 2025 at 12:02AM

Show HN: Gemini Document Processor – Generate Th Summaries from PDF/ePub with AI https://ift.tt/7Sg8YbN

Show HN: Gemini Document Processor – Generate Th Summaries from PDF/ePub with AI Hello HN! I'd like to share Gemini Document Processor, an open-source tool I've developed. This tool uses Google's Gemini AI (their latest API) to create high-quality Thai language summaries from PDF and EPUB files. Key features include: - Support for both PDF and EPUB files - Intelligent chunking for efficient Gemini API processing - Automatic image extraction from documents - Direct integration with Obsidian (export directly to vault) - Smart retry system when errors occur (switches models/increases timeouts) - Real-time progress tracking via web interface I built this tool because I needed to read many English documents and wanted detailed summaries in Thai. If you frequently read long documents or want to build a knowledge base from multiple sources, this tool could save you significant time. The output is a well-formatted Markdown file with images and metadata, ideal for storing in Obsidian, Notion, or other PKM systems. Try it by cloning the repo and running it with Python (requires a Google Gemini API key). Feedback, suggestions, and contributions are very welcome! https://ift.tt/usKB8UL April 26, 2025 at 06:20PM

Show HN: Install CLI Apps via Plain HTTP – No Docker, No Binaries, Just Curl https://ift.tt/gnvlhat

Show HN: Install CLI Apps via Plain HTTP – No Docker, No Binaries, Just Curl Tired of bloated installers and complex DevOps pipelines? I built PPORT — a terminal-based messenger — to demo a crazy simple idea: 1. Instant CLI delivery over HTTP 2. Just curl or irm, nothing else 3. TypeScript on the fly via Deno 4. Live deployment without Docker or builds How it works: Visit https://pport.top Run one command (curl -fsSL pport.top | sh) PPORT streams scripts and source files dynamically based on your client (curl, browser, Deno) No packaging. No compiling. No friction. Source on GitHub: https://ift.tt/hFn310x Curious what else could be built with this approach? Would love to hear your ideas. https://pport.top April 26, 2025 at 10:21PM

Show HN: Rocal UI – A simple template engine with Rust https://ift.tt/bkg3OrN

Show HN: Rocal UI – A simple template engine with Rust https://ift.tt/B2VXORZ April 26, 2025 at 11:56PM

Show HN: Lucidia, a WebGL visualizer inspired by Drempels https://ift.tt/kwPrABo

Show HN: Lucidia, a WebGL visualizer inspired by Drempels Made with ChatGPT, open source at https://ift.tt/CTDp1wU https://ift.tt/HKTXbgz April 26, 2025 at 12:28AM

Show HN: Open-Source, Self-Hostable Rate Limiting API https://ift.tt/QA29TvL

Show HN: Open-Source, Self-Hostable Rate Limiting API https://ift.tt/SGZyUBY April 25, 2025 at 11:03PM

Show HN: Claude Code with GUI and Block Based Prompt Editor (MIT) https://ift.tt/oebzdiw

Show HN: Claude Code with GUI and Block Based Prompt Editor (MIT) https://ift.tt/GpEHDxC April 25, 2025 at 10:28PM

Show HN: I Added Translation to My RSS Reader Project https://ift.tt/czZGYUm

Show HN: I Added Translation to My RSS Reader Project https://ift.tt/mYBFTQR April 25, 2025 at 01:59AM

Show HN: Interactive map of Palo Alto police record log PDFs https://ift.tt/6wauj3n

Show HN: Interactive map of Palo Alto police record log PDFs Got this idea when a landlord suggested I check the police logs when I asked about neighborhood safety during house hunt. I built this for myself to easily look up an address and see nearby police events. The data covers incidents from February to April 2025. Data Source: https://ift.tt/eobNEOZ... Source Code: https://ift.tt/ueasQOi (lot of slop as it was vibecoded) https://ift.tt/fNK8vy1 April 25, 2025 at 01:37AM

Show HN: GitNote- Online MD note editor that syncs to GitHub https://ift.tt/75PK6Jk

Show HN: GitNote- Online MD note editor that syncs to GitHub https://ift.tt/PBWxF9z April 25, 2025 at 01:25AM

Show HN: I reverse engineered top websites to build an animated UI library https://ift.tt/JA1IHzD

Show HN: I reverse engineered top websites to build an animated UI library Looking at websites such as Clerk, I began thinking that design engineers might be some kind of wizards. I wanted to understand how they do it, so I started reverse-engineering their components out of curiosity. One thing led to another, and I ended up building a small library of reusable, animated components based on what I found. The library is built in React and Framer Motion. I’d love to hear your feedback https://reverseui.com April 24, 2025 at 11:17PM

Show HN: Body Controlled 3D Dino Game https://ift.tt/WjQfRs1

Show HN: Body Controlled 3D Dino Game Hey HN, I am Niko. I've built this 3D Dino Game In browser using tech like three.js and MoveNet (tensorflow). Basically, it's a normal 3D dinosaur game with a twist: you need to actually perform actions irl to avoid obstacles. Duck to crouch, jump to jump, raise left hand - go left, raise right hand - go right. Game is using your phone/laptop camera to track your body movements and perform in-game actions. PS. Game is 100% client side and I don't record/track/use/save any of your data Hope you find it worth playing. (better play on PC) It's a 100% FREE browser game with no login! Please feel welcome to DM feedback or reply or anything! https://ift.tt/80BcH4Q April 23, 2025 at 02:58PM

Show HN: Durable Python Workflows https://ift.tt/26SIXJU

Show HN: Durable Python Workflows https://ift.tt/5wkjYis April 23, 2025 at 04:11AM

Show HN:[Opensource] AIgr.id–Polycentric Infrastructure for Open and Plural AI https://ift.tt/XJGSg1l

Show HN:[Opensource] AIgr.id–Polycentric Infrastructure for Open and Plural AI Hey HN! I'm Kanishka Nithin, founder of AIGr.id ( https://www.aigr.id ). We’re building AIGr.id — a polycentric network of independent, modular AI that can coordinate, exchange data, and compose into higher-level intelligence — all within a decentralized and plural ecosystem. Rings collective intelligence? In simpler terms: We’re trying to make it possible for people to produce, remix, operate, distribute and consume AI systems the way we use the internet— openly, collaboratively, and without needing to centralize everything into one mega-model owned by one mega-entity. Just like internet of intelligence. Today’s AI landscape is: Centralized, resource-heavy systems demand vast funding, compute, and talent—excluding much of the world. Controlled by a few powerful actors prioritizing profit over public good. Participation is limited, deepening inequality in AI benefits. Fragmented and siloed, with no open protocols for AI coordination We believe it's time to reimagine AI as collective intelligence, as shared commons — poly-centric, collaborative, composable, inclusive, and guided by values beyond profit. What’s different about our approach is that we’re not trying to build “the one true model” — we’re trying to make it easier for people to build, remix, run, and govern their own AI systems, together. We want a world where AGI doesn’t have to be monolithic — where different models, agents, and collectives can evolve side by side, coordinate, and even argue if they need to. Plural, by design. At the core of AIGr.id is OpenOS.AI, a distributed AI operating system. It is a full stack AIOS that spans everything from low-level compute orchestration to higher-level cognition, coordination, governance and economic policy. Think of it as a programmable substrate for building and running decentralized AI systems — across any infrastructure, in any topology. Developers can use shared protocols, primitives, and templates to compose AI systems — models, agents, cognitive workflows — and plug them into running grids. These grids can be public, private, federated, or even permissionless. Each grid can maintain its own sovereignty (values, rules, trust mechanisms), but still remain interoperable with others. It's designed for a world where we expect many intelligences to coexist, rather than one model to rule them all. We’re in beta and will be kicking off more extensive scale testing during our upcoming testnet phase. If this scratches an itch for you, or just want to jam on open systems — we’d love your feedback. If you're interested in joining the testnet, you can join our discord @ https://ift.tt/nfixAUg — we’d be excited to have you involved early. Docs, GitHub, and the paper are all linked at https://www.aigr.id Curious what you think — critiques, weird use cases, edge cases, counterpoints — all welcome. Our own background is what pushed us into this problem. Before this, we were a 4-person crew running one of the largest real-time AI inference workloads in India. We were doing around 500K inferences/sec across 80–90 models simultaneously, supporting 35+ public-sector use cases — mostly video analytics. We were operating across federated and private infrastructure in real time, processing millions of frames per second. We didn’t rely on cloud providers or commercial frameworks. Our market was distorted by deprioritized infrastructure investment and choosing to grow within our earnings means the only way to survive was by being ruthlessly efficient: creating frameworks that automated end to end production, operation, distribution and maintenance life cycle of AI -- everything at scale reliably without or with minimal human intervention — so four of us could actually live our lives, too. So in a way, AIGr.id was born out of necessity. It's the system we wish we had — one that treats intelligence as something modular, networked, composable, orchestratable, shareable, and governable – in a collective way. https://www.aigr.id April 22, 2025 at 11:13PM

Show HN: I made TypeScript's type inference more strict (and smarter) https://ift.tt/MbiPZXW

Show HN: I made TypeScript's type inference more strict (and smarter) As a TypeScript developer, I often found myself wishing the type system could do more—*especially when omitting or modifying deeply nested properties* inside complex objects and arrays. For instance, what if I want to remove a deeply nested field like `user.profile.email` and also something like `user.posts[ ].meta.shares` from a type? TypeScript doesn't really provide a built-in way to do that. So I built *DeepStrictTypes* — a utility that lets you *omit deeply nested keys*, even inside arrays, with full type inference and strictness. Here’s an example: ```ts type Example = { user: { id: string; profile: { name: string; age: number; email: string; }; posts: { title: string; content: string; meta: { likes: number; shares: number; }; }[]; }; }; // Remove 'user.profile.email' and 'user.posts[ ].meta.shares' type Omitted = DeepStrictOmit< Example, 'user.profile.email' | 'user.posts[*].meta.shares' >; ``` The resulting type: ```ts { user: { id: string; profile: { name: string; age: number; }; posts: { title: string; content: string; meta: { likes: number; }; }[]; }; } ``` Works great for: - Cleaning up types for API responses - Dynamically transforming deeply nested data - Improving type safety when handling structured JSON [ https://ift.tt/X2FrN68 ]( https://ift.tt/X2FrN68 ) Would love your feedback or ideas for improvements! https://ift.tt/yFqxuiR April 22, 2025 at 09:17AM

Show HN: Prompt Coded 3D Asteroids https://ift.tt/vtdwRsq

Show HN: Prompt Coded 3D Asteroids https://ift.tt/njHsJOT April 22, 2025 at 04:25AM

Show HN: ArTok is TikTok for research papers https://ift.tt/y9jnxFW

Show HN: ArTok is TikTok for research papers Hello everyone! I always found it hard to find new research papers outside of my usual bubble. I thought a random feed (with no recommendation algorithms) might be a fun way to explore. But I also didn’t want to waste time on completely unrelated stuff — so the idea of a fast, swipeable format came to mind. Wikitok was a real inspiration! But Arxiv and Open Review APIs weren’t as robust as Wikipedia, so I pulled the papers into a Postgres backend. Right now, I’ve indexed papers from a few recent ML conferences to see if this might be useful for others too. No signups required and it’s totally free. You can mark your favorites and add text annotations, which are saved on your device. Would love to hear your feedback! https://artok.app April 22, 2025 at 12:43AM

Show HN: Open Codex – OpenAI Codex CLI with open-source LLMs https://ift.tt/xiF3XRC

Show HN: Open Codex – OpenAI Codex CLI with open-source LLMs Hey HN, I’ve built Open Codex, a fully local, open-source alternative to OpenAI’s Codex CLI. My initial plan was to fork their project and extend it. I even started doing that. But it turned out their code has several leaky abstractions, which made it hard to override core behavior cleanly. Shortly after, OpenAI introduced breaking changes. Maintaining my customizations on top became increasingly difficult. So I rewrote the whole thing from scratch using Python. My version is designed to support local LLMs. Right now, it only works with phi-4-mini (GGUF) via lmstudio-community/Phi-4-mini-instruct-GGUF, but I plan to support more models. Everything is structured to be extendable. At the moment I only support single-shot mode, but I intend to add interactive (chat mode), function calling, and more. You can install it using Homebrew: brew tap codingmoh/open-codex brew install open-codex It's also published on PyPI: pip install open-codex Source: https://ift.tt/kjmZxN5 https://ift.tt/kjmZxN5 April 21, 2025 at 11:27PM

Show HN: TikTrotter – TikTok but for obscure travel trivia to beat doomscrolling https://ift.tt/oukqwhl

Show HN: TikTrotter – TikTok but for obscure travel trivia to beat doomscrolling I'm trying to stop doomscrolling social media, so I made a website to help me. I'm a huge traveler so I made a website that shows infinitely-scrolling obscure locations with interesting trivia in a TikTok-like manner. I've been discovering a lot of cool places in the world and dropped my social media time a lot. The website is 100% free, no ads and no sign-up. Check it out if interested, I would appreciate some feedback. Next step is to create a multiplayer trivia game where you can challenge your friends and see who knows more about the world. https://ift.tt/qm9blX3 April 20, 2025 at 09:34PM

Show HN: MidiMaker.pro – Generate structured MIDI music from text using LLMs https://ift.tt/RHN2kY3

Show HN: MidiMaker.pro – Generate structured MIDI music from text using LLMs https://midimaker.pro/ April 20, 2025 at 11:28PM