The best Hacker News stories from Show from the past day

Latest posts:

Show HN: I built an AI language teacher to get you speaking

Hello Hacker News,<p>When learning foreign languages, I made the most progress by speaking them throughout the day, every day. So I made a site where you can speak to an AI language teacher to practice both listening and speaking.<p># The product<p>What I have now:<p>* Multilingual speech recognition: You can ask a question in English and get an answer in your target language. * Feedback on your grammar. * Suggestions: See examples of what to say next to keep the conversation flowing. * Speed: Choose a lower speed for beginners or a faster one for advanced levels. * Translations: Click to see a translation into English (or another language). * Role-playing: Practice real-life situations. * Available to learn American English, British English, Australian English, French, Spanish from Spain, Spanish from Mexico, Brazilian Portuguese, European Portuguese, Russian, and more.<p>What I'd like to add:<p>* More Situations/Characters/Customizations: A "Creator mode". * Feedback on your pronunciation. * Text-based responses (Type or click – would feel like a "Create Your Own Adventure" book!) * A dictionary. * Phonetics: Zoom in and repeat a sound to help you hear phonemes and words more clearly. * …and so much more!…<p># The startup<p>Been working on this for 6-7 months now.<p>I love this project and got lots of laudatory comments about it, but still find it hard to make it take off. 31% of people come back to it, traffic is growing through word of mouth with language teachers in schools or Telegram or private intranets sharing it with others. So that's nice. But nice words alone don't pay the bills.<p>My goal is to achieve enough growth to cover costs, which would then allow me to focus 100% on the product (currently it's more like 50% of my time). But I'm not there yet.<p>A challenge I see is that most places forbid self-promotion. So I'm just not sure how on Earth I'm supposed to have a product take off. I could pay for ads, but I use AdBlock everywhere so this feels out of character. I'm a big fan of Pieter Levels (@levelsio on Twitter) because he's doing things solo, so I'm trying to emulate the same kind of success. But it seems that something is missing.<p>What features would you find most useful? How can I better market this without resorting to ads?<p>Thanks for reading! If you've got thoughts or ideas, I would love to hear them.<p>Cheers, Fabien

Show HN: I built an AI language teacher to get you speaking

Hello Hacker News,<p>When learning foreign languages, I made the most progress by speaking them throughout the day, every day. So I made a site where you can speak to an AI language teacher to practice both listening and speaking.<p># The product<p>What I have now:<p>* Multilingual speech recognition: You can ask a question in English and get an answer in your target language. * Feedback on your grammar. * Suggestions: See examples of what to say next to keep the conversation flowing. * Speed: Choose a lower speed for beginners or a faster one for advanced levels. * Translations: Click to see a translation into English (or another language). * Role-playing: Practice real-life situations. * Available to learn American English, British English, Australian English, French, Spanish from Spain, Spanish from Mexico, Brazilian Portuguese, European Portuguese, Russian, and more.<p>What I'd like to add:<p>* More Situations/Characters/Customizations: A "Creator mode". * Feedback on your pronunciation. * Text-based responses (Type or click – would feel like a "Create Your Own Adventure" book!) * A dictionary. * Phonetics: Zoom in and repeat a sound to help you hear phonemes and words more clearly. * …and so much more!…<p># The startup<p>Been working on this for 6-7 months now.<p>I love this project and got lots of laudatory comments about it, but still find it hard to make it take off. 31% of people come back to it, traffic is growing through word of mouth with language teachers in schools or Telegram or private intranets sharing it with others. So that's nice. But nice words alone don't pay the bills.<p>My goal is to achieve enough growth to cover costs, which would then allow me to focus 100% on the product (currently it's more like 50% of my time). But I'm not there yet.<p>A challenge I see is that most places forbid self-promotion. So I'm just not sure how on Earth I'm supposed to have a product take off. I could pay for ads, but I use AdBlock everywhere so this feels out of character. I'm a big fan of Pieter Levels (@levelsio on Twitter) because he's doing things solo, so I'm trying to emulate the same kind of success. But it seems that something is missing.<p>What features would you find most useful? How can I better market this without resorting to ads?<p>Thanks for reading! If you've got thoughts or ideas, I would love to hear them.<p>Cheers, Fabien

Show HN: Homelab Monitoring Setup with Grafana

Show HN: Homelab Monitoring Setup with Grafana

Show HN: Homelab Monitoring Setup with Grafana

Show HN: I built an on-device LLM based chatbot for iPhones

I’ve been playing around with local LLMs for the past couple of months and decided to build something that can run on an iPhone. It’s a universal app built with SwiftUI and the excellent ggml library. The model is an SFT fine tuned and 4 bit quantised version of the RedPajama-INCITE-Chat-3B-v1 OSS LLM. It works reasonably well on recent-ish (~3 year old) iPhones, iPads and Macs. It was launched on the App Store yesterday[1] and Product Hunt today[2]. It seems to be reasonably ok at natural language interactions, but given its size, does pretty badly at coding and reasoning. Also, it sometimes hallucinates after a few back and forth messages. The fine tuning for natural language Q&A seems to have made the base model’s already bad performance on coding tasks, even worse. I’ll add a few App Store promo codes in a comment below, if anyone would like to try it out.<p>[1]: https://apple.co/43n6BsW [2]: https://www.producthunt.com/posts/personal-gpt

Show HN: Add Favicons to HN

Show HN: Dockerless, Elixir Web Application Using Podman and Plug

Show HN: Dockerless, Elixir Web Application Using Podman and Plug

Show HN: Serverless OLAP with Seafowl and GCP

Hello HN! I'm an engineer at Splitgraph and recently started learning Rust so I could make my first contribution to Seafowl [0], an early stage analytical database. Along the way I figured out a database hosting hack on GCP and wanted to share it with HN. It's a way to achieve "true" scale to zero database hosting that could be useful for certain side projects or spiky traffic situations.<p>A recurring problem I've faced with side projects is the need for Postgres, but no desire to deploy or maintain new instances. So when I learned GCP's "always free" tier includes serverless [1] I got curious to see if I could run a database.<p>While a lot of classic databases aren't usually a great fit for serverless, Seafowl separates compute, storage and catalog (catalog == a SQLite file of metadata). [2] Last month I was able to introduce GCS bucket compat to Seafowl, which enabled me to mount the catalog via gcsfuse (i.e. an adapter that allows attaching GCS buckets to local filesystems). Upshot: while FUSE does add HTTP requests to container startup, init time remains comparatively quick, even cold starts, because fetching is limited to the single catalog SQLite file only.<p>With this approach you get a URL you can query directly from your FE if you want, e.g. fetch() can send SELECT * ... queries straight from your users' browser. You could plot a graph from a static React frontend, or observablehq.com editor, with no persistent backend needed. So at times when nobody's using your app, 100% of your stack can scale to zero with obvious cloud spend advantages. And even if you exceed free tier limits, being PAYG offers a good chance you'll come out ahead on hosting costs anyway.<p>NB: Seafowl is an early stage project, so it's not really suitable if you need transactions or fast single-row writes. Otherwise, this could be a nice way to get free database hosting at a big 3 cloud provider, especially for e.g. read-only analytical reporting queries.<p>Feedback and suggestions are appreciated. Hope it helps you! More available if you want [3].<p>[0] <a href="https://seafowl.io/docs/getting-started/introduction" rel="nofollow">https://seafowl.io/docs/getting-started/introduction</a><p>[1] <a href="https://cloud.google.com/run/pricing#cpu-requests" rel="nofollow">https://cloud.google.com/run/pricing#cpu-requests</a><p>[2] Neon is another interesting project that separates compute and storage. <a href="https://neon.tech/blog/architecture-decisions-in-neon" rel="nofollow">https://neon.tech/blog/architecture-decisions-in-neon</a><p>One issue I observed was a noticeably longer startup time vs this FUSE approach, which I believe may be related to Postgres connection setup time/roundtrips. Looking forward to trying Neon again in future.<p>[3] <a href="https://www.splitgraph.com/blog/deploying-serverless-seafowl" rel="nofollow">https://www.splitgraph.com/blog/deploying-serverless-seafowl</a>

Show HN: Serverless OLAP with Seafowl and GCP

Hello HN! I'm an engineer at Splitgraph and recently started learning Rust so I could make my first contribution to Seafowl [0], an early stage analytical database. Along the way I figured out a database hosting hack on GCP and wanted to share it with HN. It's a way to achieve "true" scale to zero database hosting that could be useful for certain side projects or spiky traffic situations.<p>A recurring problem I've faced with side projects is the need for Postgres, but no desire to deploy or maintain new instances. So when I learned GCP's "always free" tier includes serverless [1] I got curious to see if I could run a database.<p>While a lot of classic databases aren't usually a great fit for serverless, Seafowl separates compute, storage and catalog (catalog == a SQLite file of metadata). [2] Last month I was able to introduce GCS bucket compat to Seafowl, which enabled me to mount the catalog via gcsfuse (i.e. an adapter that allows attaching GCS buckets to local filesystems). Upshot: while FUSE does add HTTP requests to container startup, init time remains comparatively quick, even cold starts, because fetching is limited to the single catalog SQLite file only.<p>With this approach you get a URL you can query directly from your FE if you want, e.g. fetch() can send SELECT * ... queries straight from your users' browser. You could plot a graph from a static React frontend, or observablehq.com editor, with no persistent backend needed. So at times when nobody's using your app, 100% of your stack can scale to zero with obvious cloud spend advantages. And even if you exceed free tier limits, being PAYG offers a good chance you'll come out ahead on hosting costs anyway.<p>NB: Seafowl is an early stage project, so it's not really suitable if you need transactions or fast single-row writes. Otherwise, this could be a nice way to get free database hosting at a big 3 cloud provider, especially for e.g. read-only analytical reporting queries.<p>Feedback and suggestions are appreciated. Hope it helps you! More available if you want [3].<p>[0] <a href="https://seafowl.io/docs/getting-started/introduction" rel="nofollow">https://seafowl.io/docs/getting-started/introduction</a><p>[1] <a href="https://cloud.google.com/run/pricing#cpu-requests" rel="nofollow">https://cloud.google.com/run/pricing#cpu-requests</a><p>[2] Neon is another interesting project that separates compute and storage. <a href="https://neon.tech/blog/architecture-decisions-in-neon" rel="nofollow">https://neon.tech/blog/architecture-decisions-in-neon</a><p>One issue I observed was a noticeably longer startup time vs this FUSE approach, which I believe may be related to Postgres connection setup time/roundtrips. Looking forward to trying Neon again in future.<p>[3] <a href="https://www.splitgraph.com/blog/deploying-serverless-seafowl" rel="nofollow">https://www.splitgraph.com/blog/deploying-serverless-seafowl</a>

Show HN: Codespelunker – A command line search tool with TUI and HTTP modes

Show HN: Codespelunker – A command line search tool with TUI and HTTP modes

Show HN: FemtoGPT – Pure Rust implementation of a GPT language model

Show HN: FemtoGPT – Pure Rust implementation of a GPT language model

Show HN: Tiny Code Improver

Hey, fellow hackers! I'm excited to share my latest project, TinyCodeImprover, which has become an indispensable tool in my coding workflow.<p>What is TinyCodeImprover?<p>TinyCodeImprover leverages the power of GPT-4 to analyze and enhance your project files. By simply loading your code into the GPT-4 context, you can ask questions about your code, identify bugs, and even request GPT-4 to write code snippets across multiple files simultaneously.<p>The Story Behind its Creation<p>As a programmer, I frequently turn to GPT-4 for assistance with topics outside my expertise. However, I found the process of copying and pasting code snippets into the chat cumbersome and time-consuming. That's when I had an idea: a tool that seamlessly integrates GPT-4 into my coding environment.<p>A month ago, during a flight from Bangkok to Dubai, I developed the first prototype of TinyCodeImprover. It allowed me to feed project files directly to GPT-4 and request code improvements based on my specifications! It even wrote a Readme for itself – quite mind-blowing!<p>Refining the Process<p>To maximize the effectiveness of TinyCodeImprover, I discovered the importance of employing a critical approach. I created special commands, ".critic" and ".resolver," to initiate self-reflection, enabling GPT-4 to identify its own mistakes in approximately 30% of cases.<p>Since its inception, I've integrated TinyCodeImprover into four different projects, transforming error-fixing into an enjoyable experience, even when dealing with CSS challenges. It has proven useful not only for code but also for any type of text.

Show HN: Tiny Code Improver

Hey, fellow hackers! I'm excited to share my latest project, TinyCodeImprover, which has become an indispensable tool in my coding workflow.<p>What is TinyCodeImprover?<p>TinyCodeImprover leverages the power of GPT-4 to analyze and enhance your project files. By simply loading your code into the GPT-4 context, you can ask questions about your code, identify bugs, and even request GPT-4 to write code snippets across multiple files simultaneously.<p>The Story Behind its Creation<p>As a programmer, I frequently turn to GPT-4 for assistance with topics outside my expertise. However, I found the process of copying and pasting code snippets into the chat cumbersome and time-consuming. That's when I had an idea: a tool that seamlessly integrates GPT-4 into my coding environment.<p>A month ago, during a flight from Bangkok to Dubai, I developed the first prototype of TinyCodeImprover. It allowed me to feed project files directly to GPT-4 and request code improvements based on my specifications! It even wrote a Readme for itself – quite mind-blowing!<p>Refining the Process<p>To maximize the effectiveness of TinyCodeImprover, I discovered the importance of employing a critical approach. I created special commands, ".critic" and ".resolver," to initiate self-reflection, enabling GPT-4 to identify its own mistakes in approximately 30% of cases.<p>Since its inception, I've integrated TinyCodeImprover into four different projects, transforming error-fixing into an enjoyable experience, even when dealing with CSS challenges. It has proven useful not only for code but also for any type of text.

Show HN: SQLPage – Build Dynamic Websites with Just SQL Queries

Hey Hacker News!<p>I wanted to share the open source project I have been working on during the last year: SQLPage, a tool to build small web applications entirely in SQL.<p>Building web applications with just SQL isn't as crazy as it seems. Most simple applications can be expressed declaratively as just data queries that fill pre-defined web components.<p>I'd love to hear your feedback and thoughts on it. Would you potentially use it? How can it be improved?<p>Website: <a href="https://sql.ophir.dev/" rel="nofollow">https://sql.ophir.dev/</a> Github: <a href="https://github.com/lovasoa/SQLpage">https://github.com/lovasoa/SQLpage</a> Example app: <a href="https://conundrum.ophir.dev/" rel="nofollow">https://conundrum.ophir.dev/</a>

Show HN: SQLPage – Build Dynamic Websites with Just SQL Queries

Hey Hacker News!<p>I wanted to share the open source project I have been working on during the last year: SQLPage, a tool to build small web applications entirely in SQL.<p>Building web applications with just SQL isn't as crazy as it seems. Most simple applications can be expressed declaratively as just data queries that fill pre-defined web components.<p>I'd love to hear your feedback and thoughts on it. Would you potentially use it? How can it be improved?<p>Website: <a href="https://sql.ophir.dev/" rel="nofollow">https://sql.ophir.dev/</a> Github: <a href="https://github.com/lovasoa/SQLpage">https://github.com/lovasoa/SQLpage</a> Example app: <a href="https://conundrum.ophir.dev/" rel="nofollow">https://conundrum.ophir.dev/</a>

Show HN: SQLPage – Build Dynamic Websites with Just SQL Queries

Hey Hacker News!<p>I wanted to share the open source project I have been working on during the last year: SQLPage, a tool to build small web applications entirely in SQL.<p>Building web applications with just SQL isn't as crazy as it seems. Most simple applications can be expressed declaratively as just data queries that fill pre-defined web components.<p>I'd love to hear your feedback and thoughts on it. Would you potentially use it? How can it be improved?<p>Website: <a href="https://sql.ophir.dev/" rel="nofollow">https://sql.ophir.dev/</a> Github: <a href="https://github.com/lovasoa/SQLpage">https://github.com/lovasoa/SQLpage</a> Example app: <a href="https://conundrum.ophir.dev/" rel="nofollow">https://conundrum.ophir.dev/</a>