Show HN: magick.css – Minimalist CSS for Wizards https://ift.tt/FYZX9n5

Show HN: magick.css – Minimalist CSS for Wizards https://ift.tt/BtEX2al March 23, 2024 at 12:13AM

Show HN: JobLander – Chrome Extension for Real-Time Job Interview Hints https://ift.tt/VrK8HZJ

Show HN: JobLander – Chrome Extension for Real-Time Job Interview Hints https://ift.tt/OgW8wvH March 22, 2024 at 01:41AM

Show HN: Turn a video of an app into a functional prototype with Claude Opus https://ift.tt/8AbjgtD

Show HN: Turn a video of an app into a functional prototype with Claude Opus Hey everyone, I’m the maintainer of the popular screenshot-to-code repo on Github (46k+ stars). When Claude Opus was released, I thought to myself what if you could send in a video of yourself using a website or app, would the LLM be able to build it as a functional prototype? To my surprise, it worked quite well. Here are two examples: * In this video, you can see the AI replicating Google with auto-complete suggestions and a search results page (failed at putting the results on a separate page). https://ift.tt/BudnfpL * Here, we show it a multi-step form ( https://ift.tt/vaFt6gk ) and ask Claude to re-create it. It does a really good job! https://ift.tt/Vo8SeEn The technical details: Claude Opus only allows you to send a max of 20 images so 20 frames are extracted from the video, and passed along with a prompt that uses a lot of Claude-specific techniques such as using XML tags and pre-filling an assistant response. In total, 2 passes are performed with the second pass instructing the AI improve on the first attempt. More passes might help as well. While I think the model has Google.com memorized but for many other multi-page/screen apps, it tends to work quite well. You can try it out by downloading the Github repo and setting up a Anthropic API key in backend/.env Be warned that one creation/iteration (with 2 passes) can be quite expensive ($3-6 dollars). https://ift.tt/hp5aVAk March 22, 2024 at 12:36AM

Show HN: OpenAI API + AWS Stack = 50k+ Word E-Books 8 mins https://ift.tt/JygV5m0

Show HN: OpenAI API + AWS Stack = 50k+ Word E-Books 8 mins I found a solution to AI content wordcount limit (typically around 500 ~ 3000 words) to help generate complete E-Book with AI using Openai + AWS stack. Demo video here https://youtu.be/V1FAAhiyzVc https://inkflow.io/ March 21, 2024 at 03:44AM

Show HN: Personal Knowledge Base Visualization https://ift.tt/vMxHne3

Show HN: Personal Knowledge Base Visualization My personal knowledge base is hosted on GitHub at https://ift.tt/MiACYwg . It scans the documents I like every day using GitHub Action, Zotero, HackerNews upvote and Github Likes. It's not yet optimized for smartphones. It cost me $5 to host it for a year. https://ift.tt/h6k35GJ March 21, 2024 at 03:28AM

Show HN: GritQL, a Rust CLI for rewriting source code https://ift.tt/WZrgeSO

Show HN: GritQL, a Rust CLI for rewriting source code Hi everyone! I’m excited to open source GritQL, a Rust CLI for searching and transforming source code. GritQL comes from my experiences with conducting large scale refactors and migrations. Usually, I would start exploring a codebase with grep. This is easy to start with, but most migrations end up accumulating additional requirements like ensuring the right packages are imported and excluding cases which don’t have a viable migration path. Eventually, to build a complex migration, I usually ended up having to write a full codemod program with a tool like jscodeshift. This comes with its own problems: - Most of the exploratory work has to be abandoned as you figure out how to represent your original regex search as an AST. - Reading/writing a codemod requires mentally translating from AST names back to what source code actually looks like. - Performance is often an afterthought, so iterating on a large codemod can be painfully slow. - Codemod frameworks are language-specific, so if you’re hopping between multiple languages—or trying to migrate a shared API—you have to learn different tools. GritQL is an attempt to develop a powerful middle ground: - Exploratory analysis is easy: just put a code snippet in backticks and use $metavariables for placeholders. - Incrementally add complexity by introducing side conditions with where clauses. - Reuse named patterns to avoid rebuilding queries, and use shared patterns from our standard library for common tasks like ensuring modules are imported. - Iterate on large codebases quickly: we use Rust for maximum performance GritQL has already been used on thousands of repositories for complex migrations[1] but we're excited to collaborate more with the open source community. [1] Ex. https://ift.tt/2qou3G0 https://ift.tt/sAYQFlu March 21, 2024 at 12:53AM

Show HN: Automated Software Documentation for GitHub Codebases https://ift.tt/1gXmjAl

Show HN: Automated Software Documentation for GitHub Codebases Hey Hackers, My team and I have been working on an automated software documentation and impact analysis platform for the last 3 years. Our long-term goal is to enter safety/mission-critical applications, where improper documentation can lead to disastrous outcomes, e.g., costly reworks/overruns or endangering human lives. But, in an effort to recognize revenue in the near term with our existing functionality, we have found initial traction with use cases focused on reverse engineering legacy systems. Where getting up to speed with an existing system requires a team of engineers to manually review large amounts of code, taking weeks or months to come to grips with. ______________________________________________ Our Self-Service release is a no-frills offering to leverage a subset of our document generation capabilities. Using only the code, SAFA is able to: -Summarize Code Files -Generate an overall project summary -Generate Upstream Documentation, like Features and Functional Requirements -Map relationships between all code and generated documentation with explanations Our approach leverages our own LLM pipeline, which applies a variety of clustering/refinement techniques, embedding models, and LLMs to keep your entire system within context when generating documentation, change summaries, api flow, and more. We do not use customer data to train or refine our models. We currently only support Github integrations for self-service but will implement flat-file support in the near term. When using self-service, you will receive Code Summaries and a Project Overview for free, but we charge for generating documentation and relationships: 20 cents per code file and generated document (100 File Codebase = $35). Currently, self-service has a 1000 code file limit. ________________________________________________ If you want to see the quality of the documents SAFA generates before trying it with your code, feel free to check out our public codebases page ( https://ift.tt/IwtcrHf ). We have serious ones like Autoware's AV Control Module, and more fun ones, like Super Mario 64. Otherwise, our app is directly accessible via https://app.safa.ai (apologies, we do require an account to be made). I very much look forward to your feedback and insights. Feel free to email me directly at aarik@safa.ai. https://www.safa.ai March 21, 2024 at 12:24AM

Show HN: Real-time voice chat with AI, no transcription https://ift.tt/ZAvqbwz

Show HN: Real-time voice chat with AI, no transcription Hi HN -- voice chat with AI is very popular these days, especially with YC startups ( https://twitter.com/k7agar/status/1769078697661804795 ). The current approaches all do a cascaded approach, with audio -> transcription -> language model -> text synthesis. This approach is easy to get started with, but requires lots of complexity and has a few glaring limitations. Most notably, transcription is slow, is lossy and any error propagates to the rest of the system, cannot capture emotional affect, is often not robust to code-switching/accents, and more. Instead, what if we fed audio directly to the LLM - LLM's are really smart, can they figure it out? This approach is faster (we skip transcription decoding) and less lossy/more robust because the big language model should be smarter than a smaller transcription decoder. I've trained a model in just that fashion. For more architectural information and some training details, see this first post: https://tincans.ai/slm . For details about this model and some ideas for how to prompt it, see this post: https://tincans.ai/slm3 . We trained this on a very limited budget but the model is able to do some things that even GPT-4, Gemini, and Claude cannot, eg reasoning about long-context audio directly, without transcription. We also believe that this is the first model in the world to conduct adversarial attacks and apply preference modeling in the speech domain. The demo is unoptimized (unquantized bf16 weights, default Huggingface inference, serverless speed bumps) but achieves 120ms time to first token with audio. You can basically think of it as Mistral 7B, so it'll be very fast and can also run basically anywhere. I am especially optimistic about embedded usage -- not needing the transcription step means that the resulting model is smaller and cheaper to use on the edge. Would love to hear your thoughts and how you would use it! Weights are Apache-2 and on Hugging Face: https://ift.tt/wsCt1b9... https://ift.tt/Mdi3NFt March 20, 2024 at 12:37AM

Show HN: Krata Maps – open-source Figma like GeoJSON Editor https://ift.tt/6YhyZaR

Show HN: Krata Maps – open-source Figma like GeoJSON Editor https://krata.app March 19, 2024 at 11:58PM

Show HN: Principal — Modern Wealth Tracking https://ift.tt/Fms9uxI

Show HN: Principal — Modern Wealth Tracking https://ift.tt/yPBiS5Z March 19, 2024 at 10:50PM

Show HN: Arthas.ai – An open-source alternative to character.ai https://ift.tt/wNZD731

Show HN: Arthas.ai – An open-source alternative to character.ai https://ift.tt/2lM1yeA March 19, 2024 at 07:29AM

Show HN: Extend Zigbee sensor range with LoRaWAN https://ift.tt/jFkbs0A

Show HN: Extend Zigbee sensor range with LoRaWAN https://ift.tt/CzTtfx5 March 18, 2024 at 02:36PM

Show HN: Next-Gen AI Training: LLM-RLHF-Tuning with PPO and DPO https://ift.tt/iezIWBa

Show HN: Next-Gen AI Training: LLM-RLHF-Tuning with PPO and DPO https://ift.tt/FqNDrWR March 19, 2024 at 12:40AM

Show HN: Pipedream now has 2000+ API integrations https://ift.tt/OuLyxQz

Show HN: Pipedream now has 2000+ API integrations https://ift.tt/SDwcnOr March 18, 2024 at 11:42PM

Show HN: Native implementation of with checkboxes https://ift.tt/LhyKgU0

Show HN: Native implementation of

Show HN: Website for creating self-signed certificates https://ift.tt/cNHbewg

Show HN: Website for creating self-signed certificates If you're developing locally and need to use HTTPS for whatever, then this tool is hopefully useful to you. I made it because there's a lot of bad info online about generating self-signed certificates. For instance, a lot of guides don't use the SAN list extension or show you how to create a proper certificate chain. Firefox doesn't allow a CA certificate to be used as an end certificate. Getting a working certificate can get pretty confusing, especially for newcomers to certificates or webdev. Having a website for this also means the process of getting a certificate is the same, no matter if you're on a Unix-like OS or Windows. A WebAssembly module built with C++ and Mbed TLS is used to create the keys and certificates. TypeScript and Preact is used for the UI. https://ift.tt/pLetjPq March 18, 2024 at 12:54AM

Show HN: Interactive Smartlog VSCode Extension – An Interactive Git GUI https://ift.tt/7dJaq5w

Show HN: Interactive Smartlog VSCode Extension – An Interactive Git GUI Interactive Smartlog is a graphical VSCode extension that presents a simplified view of the Git log, directly highlighting the branches and commits that are most relevant to your current work. And it's not just a visual tool — it's fully interactive, allowing you to add/switch/remove branches, stage/unstage files, and manage commits directly from the GUI. This tool draws inspiration from Meta's Interactive Smartlog built for the Sapling source control system, and I've adapted it to work with Git. Transitioning the functionality from Sapling to Git wasn't just about a one-to-one feature transfer; it involved changing how data is queried & presented, as well as introducing UI interactions for several Git concepts (like branches, staging/unstaging changes, etc) which are not present in the Sapling source control system. Originally a personal project to enhance my own workflow, I've published the extension on the VSCode marketplace for anyone who would like to use it. I'm keen to hear your feedback and suggestions, as community input is invaluable in shaping its future updates. https://ift.tt/niRlZ0Y March 17, 2024 at 06:28AM

Show HN: Parikar, Read long form articles or blogs in a better, measurable way https://ift.tt/10tL4yA

Show HN: Parikar, Read long form articles or blogs in a better, measurable way https://ift.tt/W7tcGoq March 15, 2024 at 06:10PM

Show HN: Htmx with ManTL Templates https://ift.tt/FxwCMqk

Show HN: Htmx with ManTL Templates HTMX revitalizes server-side rendering via templates. ManTL is a Java-centric, 100% type-safe templating language with comprehensive IntelliJ integration. It was designed with HTMX (formerly intercooler) in mind. Authors include both Manifold creator and HTMX creator. https://ift.tt/CXlj5ZN March 17, 2024 at 12:01AM

Show HN: SatCat5, the open-source FPGA Ethernet switch https://ift.tt/M7CGwFL

Show HN: SatCat5, the open-source FPGA Ethernet switch We've just launched v2.5 of SatCat5, the open-source FPGA Ethernet switch [1]. SatCat5 contains various FPGA building blocks that let you build a custom mixed-media Ethernet switch. It was originally intended for cubesats [2] but has many other potential applications. The headline feature for this release is support for the IEEE-1588 Precision Time Protocol (PTP). SatCat5 has demonstrated end-to-end synchronization to within 50 ps-rms, which is approaching the world-leading performance of CERN's White Rabbit Project [3]. Except we're doing time-transfer over regular, non-synchronous Ethernet. The key breakthrough is a new technology for digital timestamps that we've published in IEEE Access [4]. This project was featured on HN back in 2023 [5]. Since then, we've changed to the CERN-OHL-W v2.0 license, which has much better legal clarity for FPGA projects. [1] https://ift.tt/gj6EozN [2] https://ift.tt/stAOM4D [3] https://ift.tt/yO0xrH8... [4] https://ift.tt/N2jWEJZ [5] https://ift.tt/hmOuZ5w https://ift.tt/KRCGQBf March 17, 2024 at 05:17AM