Music046 | Nigeria No1. Daily Updates | Contact Us

Wednesday, 19 April 2023

Show HN: Create Comics Using Stable Diffusion https://bit.ly/3UPcA6e

Show HN: Create Comics Using Stable Diffusion https://bit.ly/3mHOMVv April 20, 2023 at 07:41AM

Show HN: Question Extractor: turn text into LLM finetuning data https://bit.ly/41HmVn3

Show HN: Question Extractor: turn text into LLM finetuning data https://bit.ly/3Lfzlgu April 20, 2023 at 01:47AM

Show HN: ChatGPT to control your own app (text-to-action library) https://bit.ly/3ouNvRQ

Show HN: ChatGPT to control your own app (text-to-action library) ActionIt is a text-to-action library built to make it easier to perform actions based on natural language input. It opens the way for applications that don't only retrieve information but actually interact with functions, extracting necessary parameters or asking follow-up questions where necessary. In simple terms, your functions are presented to ChatGPT and the correct one is chosen and executed based on a natural language input. Would love any feedback or feature requests:) https://bit.ly/40pzNx8 April 19, 2023 at 11:04PM

Show HN: Checksum – generate and maintain end-to-end tests using AI https://bit.ly/3ofMRHR

Show HN: Checksum – generate and maintain end-to-end tests using AI Hey HN! I’m Gal, co-founder at Checksum (https://bit.ly/3UQ8MS7). Checksum is a tool for automatically generating and maintaining end-to-end tests using AI. I cut my teeth in applied ML in 2016 at a maritime tech company called TSG, based in Israel. When I was there, I worked on a cool product that used machine learning to detect suspicious vehicles. Radar data is pretty tough for humans to parse, but a great fit for AI – and it worked very well for detecting smugglers, terrorist activity, and that sort of thing. In 2021, after a few years working in big tech (Lyft, Google), I joined a YC company, seer W21, as CTO. This is where I experienced the unique pain of trying to keep end-to-end tests in a good state. The app was quite featureful, and it was a struggle to get and maintain good test coverage. Like the suspicious maritime vehicle problem I had previously encountered, building and maintaining E2E tests had all the markings of a problem where machines could outperform humans. Also, in the early user interviews, it became clear that this problem wasn’t one that just went away as organizations grew past the startup phase, but one that got even more tangled up and unpleasant. We’ve been building the product for a little over a year now, and it’s been interesting to learn that some problems were surprisingly easy, and others unusually tough. To get the data we need to train our models, we use the same underlying technology that tools like Fullstory and Hotjar use, and it works quite well. Also, we’re able to get good tests from relatively few user sessions (in most cases, fewer than 200 sessions). Right now, the models are really good at improving test coverage for featureful web-apps that don’t have much coverage (ie; generating and maintaining a bunch of new tests), but making existing tests better has been a tougher nut to crack. We don’t have as much of a place in organizations where test coverage is great and test quality is medium-to-poor, but we’re keen to develop in that direction. We’re still early, and spend basically all of our time working with a small handful of design partners (mostly medium-sized startups struggling with test coverage), but it felt like time to share with the HN community. Thanks so much, happy to answer any questions, and excited to hear your thoughts! April 19, 2023 at 04:05PM

Show HN: Open-source Auth0 alternative Ory Kratos v0.13 released – nearing v1.0 https://bit.ly/43IrNdt

Show HN: Open-source Auth0 alternative Ory Kratos v0.13 released – nearing v1.0 https://bit.ly/43LrRJd April 19, 2023 at 03:30PM

Show HN: A web decision game 99% coded by GPT4. Uses agent to decide win/loss https://bit.ly/3ULgInS

Show HN: A web decision game 99% coded by GPT4. Uses agent to decide win/loss Yeah... so I know some software development concepts well I haven't written any code in 10 years, so like half the time was just getting a development setup. At first it suggested PyCharm and honestly it wasted a lot of time. Eventually I got VS Code and GPT just seems to understand it so much better. The real secret to getting good responses with GPT-4 during this I found is to restart the conversation fresh with a complete description of what you need (2-3 paragraphs of detail is great) and the rest as code. [detailed description of what you need, make sure it's detailed and specific add examples if possible] #### [insert all the code, the more you can fit the better] That first code block it gives you back on the first output is the cleanest by far. If there is an error and you submit it back in the same chat conversation, it just gets diluted/saturated over time, hallucinations go up etc. So if there is a bug rather than continue in the same convo, repeat this process in a brand new conversation. Each time it gives a much cleaner, fresher look at the code and goals needed. If your codeblock is really small then this isn't so important, but I'm trying to maximize the amount of code per prompt for best responses. I also make sure to split files by concerns so they don't get too big for the prompt window otherwise it's annoying. #### And lastly the other interesting thing about this project is this simulates an Agent loop where it is constantly trying to determine if the player won or lost, decide what the next most cohesive step is based on the human feedback (click emoji) and looping it. Actually that was my main interest for the project and I just wanted to get something published as a secondary goal. Most of my time was probably spent playing with the prompt and trying to to see if I could get it to determine if the goal was achieved but its actually a hard problem and I have some cool ideas for the next project. https://bit.ly/3KMpBsJ April 19, 2023 at 07:11AM

Show HN: Karma Design Suite – A powerful wireframe and UI toolkit for designers https://bit.ly/3UPI7oG

Show HN: Karma Design Suite – A powerful wireframe and UI toolkit for designers We've designed an extensive wireframe kit and a more extensive set of UI kits. All feedback is appreciated. https://bit.ly/3GWt1YV April 19, 2023 at 12:01PM

Tuesday, 18 April 2023

Show HN: No-cloud P2P file transfer in the browser using latest WebTorrent v2 https://bit.ly/3UReUtp

Show HN: No-cloud P2P file transfer in the browser using latest WebTorrent v2 https://bit.ly/3CQeAUE April 18, 2023 at 05:57PM

Show HN: Database for analyzing US companies, visualize using Apache SuperSet https://bit.ly/41GGr3c

Show HN: Database for analyzing US companies, visualize using Apache SuperSet My main motivation was that I wanted to be able to drill down and filter across all the available stocks, look at the data for myself, and narrow down on the stocks I am interested based on my own sets of criteria, and make data-driven analysis for my personal investment strategies. I used PostgreSQL as the backend database for ELT data pipelines, and used Citus Data cstore_fdw for columnar compression for the final dataset. All financial data is coming from SEC Edgar, https://bit.ly/3Aa44VX . I used Python for downloading most of the data. I also run the data load development locally on my home Ubuntu server that I built 5 years ago. I bought 4TB of M2 disks for best database performance, with PRIME B360M-A motherboard and Intel Chip Coffee Lake S. I built the website simply using WordPress, and I run Apache Superset using gunicorn via Apache Webserver reverse proxy. The registration form I had to build myself with PHP and some JavaScript, because it needed to automatically create a SuperSet user upon registration. Otherwise, I would need to input everyone manually. I used Python again for the data integration. Please don't use the database directly as an investment tool, as its in Beta, and the data still needs to undergo heavy data quality checks, please confirm all the numbers yourself, as I provide a link for every company to the SEC filings. https://bit.ly/41GGsUO April 18, 2023 at 10:16PM

Show HN: AI Playground by Vercel Labs https://bit.ly/3on4HJ6

Show HN: AI Playground by Vercel Labs Hey, Jared Palmer (creator of this playground) here. Really excited to ship this. I’ve been building this over the past few weeks to compare LLMs from different providers like OpenAI, Anthropic, Cohere, etc. At Vercel, I manage our Frameworks division (including Next.js, Svelte, and Turbo) and wanted to also dogfood some of the latest features in a slightly larger application. This playground takes a lot of inspiration from https://bit.ly/41n2V9E and is built on Tailwind, ui.shadcn.com, and some upcoming Vercel products we’re announcing soon. We’re going to continue adding models to compare and add other frameworks to generate code snippets from. https://bit.ly/3onP7wO April 18, 2023 at 11:38PM

Show HN: The Fuck Cards – make a card for a friend or enemy https://bit.ly/3UJLLQM

Show HN: The Fuck Cards – make a card for a friend or enemy The Fuck Card started years ago as a physical card I printed for some friends. Now it's this simple web app you can use to express yourself. Quickly make a card, copy the link and send it to someone who deserves it. It's fun and there's lots you can say with it. I built it built in 100% handcrafted in Vanilla HTML, CSS and JS. No frameworks, no BS. Fonts are provided by Google Fonts. Image generation thanks to html2canvas. No-tracking analytics by Matomo. It started as a weekend project to train my JS skills. I'd love to know your thoughts. https://bit.ly/3L9OcZS April 18, 2023 at 12:36PM

Monday, 17 April 2023

Show HN: Quorbo – a quick and quirky quest for the quote https://bit.ly/41BayJ7

Show HN: Quorbo – a quick and quirky quest for the quote Hey HN, Today I'm launching Quorbo (www.quorbo.com): a simple letter-revealing game (think Wheel of Fortune with some twists) where you get 6 turns to guess the day's quote! It's my first post-parenthood side project and first web game. Being a working dad has caused me (for the first time, believe it or not) to focus on simplicity. Up until about a year ago, endless free time secretly plagued me... because I love _building_, and more free time meant: more room to add complexity. Not anymore! Quorbo is the first of my initial batch of three simple word games, and I can't wait to make more. Let me know what you think! (improvements, bugs / quirky behavior / stumbling blocks, any and all feedback welcome!) Enjoy! https://bit.ly/41BaCIR April 17, 2023 at 10:46PM

Show HN: Instant AI Powered Support https://bit.ly/3GON0IR

Show HN: Instant AI Powered Support Create a virtual assistant for your product with a single click 1. Tell us your website 2. Choose the pages you'd like Bubbly to learn from 3. We will instantly create a GPT3 AI Bot that can answer any question about your product or service. https://bit.ly/3mHjJcc April 17, 2023 at 09:13PM

Show HN: Magic Happens – let ChatGPT manage your Kubernetes cluster https://bit.ly/3GPND4M

Show HN: Magic Happens – let ChatGPT manage your Kubernetes cluster I built this kubernetes operator as a proof of concept this weekend.. It only has a single required item in the spec, a freeform description field. The operator will use chatgpt to generate a spec, then immediately apply it to the cluster. It makes some attempt to correct errors if there's a problem with the syntax. It will leave additional comments, questions or instructions in the status field of the object. I built this in a weekend and it's still quite unrefined. It's in no way production ready, please don't use it for anything real, but it works better than you would think, considering how simple it is. If you're going to use it, run it on a local cluster like 'kind'. Some descriptions to try: * install a redis namespace with a redis cluster and a service in it * create an argocd application in the argocd namespace to install velero. * write a python script that lists all ec2 instances in us-east-1, and run it as a k8s job with the aws credentials already saved in the default namespace.. a somewhat longer description that also worked: given the following spec: --- kind: MagicHappens apiVersion: gptmagic.io/v1 metadata: name: foo spec: description: this is a freeform description field that will be sent to chatgpt to generate kubernetes resources dryRun: false --- Can you create more magic happens resources, each of which describes an argocd application that needs to be created to install a helm chart for one of the standard cluster addons that need to be installed on a cluster for it to be production ready. The description should be be freeform text like the following: "Create an argocd application in the argocd namespace to install istio from the helm chart with all the defaults" or "Create an argocd application in the argocd namespace to install prometheus and grafana, with an ingress enabled for grafana". Be very thorough and included as many apps that might be needed for a prod ready cluster using industry standard CNCF projects if possible. (this produces a list of additional resources for the operator, which the operator then goes on to create argocd applications for -- it also left comments with instructions on one of the resources for how configure it to work with your cloud provider something to note is that since you can run arbitrary containers with arbitrary commands, and chatgpt can write arbitrary code, you don't have to limit yourself to k8s stuff.. if you've got saas credentials on the cluster, you can just tell it to run a python script as a job to do whatever you want. Since most people are cowards, there's a dryRun field that defaults to true, so it only attaches the spec to the object. It is scary how well this works. https://bit.ly/3mzGajD April 17, 2023 at 07:39PM

Show HN: Trivai.app – AI powered trivia questions, with references https://bit.ly/41gTsAo

Show HN: Trivai.app – AI powered trivia questions, with references Hi HN! As many of you, I've had a lot of fun playing around with LLMs the past few months and I wanted to show you what I've built. I made a trivia website using GPT3 a while back just to have something to play with. My initial interest was to see if I could get structured responses to build a UI around, and if I could get the LLM to refer back to what piece of text it used to create questions and answers with. The initial results were pretty good, but not good enough. Fast forward a few months, GPT 3.5 was released to the public and I was released from my work. I decided to pick this up again and have been making some changes. - I've generated almost 3000 questions. - I initially only let signed up users generate questions due to cost concerns. Since 3.5 is much cheaper, I've opened up the question generation for everybody. - I built a prompt comparison tool so I could tweak the prompt to get better responses. - I've added some more data to the questions. This includes a more free form explanation to the correct answer (separate from the references), and categories for all questions. - I've been working on a question improvement process. This means I collect issues, generate new variations of the question and let people vote on them. Voting and question improvement is currently only available to signed in users. I have many more ideas I'd like to explore, but I would appreciate your feedback and would be happy to answer any questions about the site or its development. You can access the references by pressing the explanation text when you've answered a question correctly. https://bit.ly/3MOUIq4 April 17, 2023 at 06:43PM

Show HN: Embedding an ArXiv paper and chatting with it https://bit.ly/3KDlSh0

Show HN: Embedding an ArXiv paper and chatting with it https://twitter.com/pwang_szn/status/1647902577760116737 April 17, 2023 at 04:00PM

Show HN: Serverless Monitoring Designed for Developers and DevOps Teams https://bit.ly/3KLbdB2

Show HN: Serverless Monitoring Designed for Developers and DevOps Teams https://bit.ly/3MP43hO April 17, 2023 at 11:17AM

Music046 | Nigeria No1. Daily Updates | Contact Us - +2349077287056