The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Watering my Christmas tree with ESPHome
Show HN: Watering my Christmas tree with ESPHome
Show HN: Open source alternative to ChatGPT and ChatPDF-like AI tools
Hey everyone,<p>We have been building SecureAI Tools -- an open-source application layer for ChatGPT and ChatPDF-like AI tools.<p>It works with locally running LLMs as well as with OpenAI-compatible APIs. For local LLMs, it supports Ollama which supports all the gguf/ggml models.<p>Currently, it has two features: Chat-with-LLM, and Chat-with-PDFs. It is optimized for self-hosting use cases and comes with basic user management features.<p>Here are some quick demos:<p><pre><code> * Chat with documents using OpenAI's GPT3.5 model: https://www.youtube.com/watch?v=Br2D3G9O47s
* Chat with documents using a locally running Mistral model (M2 MacBook): https://www.youtube.com/watch?v=UvRHL6f_w74
</code></pre>
Hope you all like it :)
Show HN: We've built an Open Source plugin to make using AI easier for VFX
Hi, I’m Bryan Lyon, the CTO of DeepMake. We’re making plugins for VFX software suites (Right now we have a pre-release of our After Effects plugin ready) that enable you to use Open Source AI tools without leaving the workflow. It makes all the AI tools work just like another plugin in the VFX software.<p>In the past, I worked on VFX adjacent AI and was more than once asked to make AI tools easier to use so the VFX experts could use them. In many cases my job was little more than making it easy to install and make sense to use. After writing dozens of “one-off” scripts that made an AI tool usable I decided there should be a better way. To that end we’ve simplified the process. Right now our public release is still not the easiest to install, but once you’ve installed one plugin and the backend, installing new plugins is as simple as extracting a zip file or cloning a repo (and we’re going to make it even easier).<p>Our target audience isn’t non-technical people, but rather people who don’t have the time or experience to go through installing an AI tool which may not even include an easy way to send your own data through the pipeline. We hope to make VFX easier for people who can’t really do VFX now due to either a lack of time or experience. We also want to make VFX more powerful for VFX experts.<p>We’ve built the backend to make plugins extremely easy to make and hope that the community will be able to take advantage of an easy way to integrate with VFX tools. IN the spirit of open source we’ve released our code as open source (We’re cleaning up the AE plugin side, but it’ll be released too).<p>We plan on monetizing based on managing massive plugins across compute farms for big VFX shops and other features that benefit those larger teams, the core of the system will remain open source and freely available.<p>So far, we’ve released a Stable Diffusion plugin, and have more including Masking, Super Resolution, and more coming up in the pipeline.<p>I hope you like our software and look forward to hearing from you.
Show HN: We've built an Open Source plugin to make using AI easier for VFX
Hi, I’m Bryan Lyon, the CTO of DeepMake. We’re making plugins for VFX software suites (Right now we have a pre-release of our After Effects plugin ready) that enable you to use Open Source AI tools without leaving the workflow. It makes all the AI tools work just like another plugin in the VFX software.<p>In the past, I worked on VFX adjacent AI and was more than once asked to make AI tools easier to use so the VFX experts could use them. In many cases my job was little more than making it easy to install and make sense to use. After writing dozens of “one-off” scripts that made an AI tool usable I decided there should be a better way. To that end we’ve simplified the process. Right now our public release is still not the easiest to install, but once you’ve installed one plugin and the backend, installing new plugins is as simple as extracting a zip file or cloning a repo (and we’re going to make it even easier).<p>Our target audience isn’t non-technical people, but rather people who don’t have the time or experience to go through installing an AI tool which may not even include an easy way to send your own data through the pipeline. We hope to make VFX easier for people who can’t really do VFX now due to either a lack of time or experience. We also want to make VFX more powerful for VFX experts.<p>We’ve built the backend to make plugins extremely easy to make and hope that the community will be able to take advantage of an easy way to integrate with VFX tools. IN the spirit of open source we’ve released our code as open source (We’re cleaning up the AE plugin side, but it’ll be released too).<p>We plan on monetizing based on managing massive plugins across compute farms for big VFX shops and other features that benefit those larger teams, the core of the system will remain open source and freely available.<p>So far, we’ve released a Stable Diffusion plugin, and have more including Masking, Super Resolution, and more coming up in the pipeline.<p>I hope you like our software and look forward to hearing from you.
Show HN: Fine-grained stylistic control of LLMs using model arithmetic
We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: <a href="https://arxiv.org/abs/2311.14479" rel="nofollow noreferrer">https://arxiv.org/abs/2311.14479</a>. Feedback and potential applications are welcome.
Show HN: Fine-grained stylistic control of LLMs using model arithmetic
We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: <a href="https://arxiv.org/abs/2311.14479" rel="nofollow noreferrer">https://arxiv.org/abs/2311.14479</a>. Feedback and potential applications are welcome.
Show HN: Fine-grained stylistic control of LLMs using model arithmetic
We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: <a href="https://arxiv.org/abs/2311.14479" rel="nofollow noreferrer">https://arxiv.org/abs/2311.14479</a>. Feedback and potential applications are welcome.
Show HN: Minimalist Calendars Generator
Show HN: Minimalist Calendars Generator
Show HN: Open-source alternatives to tools You pay for
hey makers,
I've spent the whole night to compile this list out of
> winners of Product Hunt
> best dev tools on DevHunt
> recently active on GitHub
> most internet backlinks
> most mentions as "alternative to .."<p>Let me know if I should add anything there.
Show HN: Open-source alternatives to tools You pay for
hey makers,
I've spent the whole night to compile this list out of
> winners of Product Hunt
> best dev tools on DevHunt
> recently active on GitHub
> most internet backlinks
> most mentions as "alternative to .."<p>Let me know if I should add anything there.
Show HN: A commenting system that works via email
Hi everyone,<p>I made a commenting system that accepts submissions via email, instead of requiring a login. The back story is I wanted some interactivity for my site/blog, but I felt like requiring a signup wouldn't be a good UX.<p>I'm looking to get feedback on it from the HN community. Please feel free to ask questions and let me know your thoughts, especially what you don't like about it. If it's a decent UX then I would like to make it OSS, as I feel that it could potentially fill a void, especially for beautiful small websites.<p>Here's the basic flow of data:<p>1. When the site is generated, mailto links embed information for where the future comment will go<p>2. When a user clicks on a "comment" or "reply" link, it opens a draft comment in their mail client. Instructions are pre-baked into the email body.<p>3. When a user hits send, the email is received by my software, which parses the email, validates it for tampering against a pre-computed hash, and then opens a pull request.<p>The user gets an "auto-reply" email, informing them that the submission was successful, along with a link to preview it. The site moderator (so, in this case, me) gets an email, with links to the PR. When the comment is approved, the site is rebuilt and deployed.<p>Other info and potential gotchas:<p>* Emails are all hashed for privacy (with a secret "pepper") that's occasionally rotated<p>* Comments are represented as individual files, so there are no merge conflicts<p>* DKIM, DMARC, and SPF are all checked to help prevent spoofing<p>There's a FAQ on the link above that has more information, and you can also see a demo on my personal website: <a href="https://spenc.es/writing/email-as-a-commenting-system/" rel="nofollow noreferrer">https://spenc.es/writing/email-as-a-commenting-system/</a><p>Thanks for reading!
Show HN: A commenting system that works via email
Hi everyone,<p>I made a commenting system that accepts submissions via email, instead of requiring a login. The back story is I wanted some interactivity for my site/blog, but I felt like requiring a signup wouldn't be a good UX.<p>I'm looking to get feedback on it from the HN community. Please feel free to ask questions and let me know your thoughts, especially what you don't like about it. If it's a decent UX then I would like to make it OSS, as I feel that it could potentially fill a void, especially for beautiful small websites.<p>Here's the basic flow of data:<p>1. When the site is generated, mailto links embed information for where the future comment will go<p>2. When a user clicks on a "comment" or "reply" link, it opens a draft comment in their mail client. Instructions are pre-baked into the email body.<p>3. When a user hits send, the email is received by my software, which parses the email, validates it for tampering against a pre-computed hash, and then opens a pull request.<p>The user gets an "auto-reply" email, informing them that the submission was successful, along with a link to preview it. The site moderator (so, in this case, me) gets an email, with links to the PR. When the comment is approved, the site is rebuilt and deployed.<p>Other info and potential gotchas:<p>* Emails are all hashed for privacy (with a secret "pepper") that's occasionally rotated<p>* Comments are represented as individual files, so there are no merge conflicts<p>* DKIM, DMARC, and SPF are all checked to help prevent spoofing<p>There's a FAQ on the link above that has more information, and you can also see a demo on my personal website: <a href="https://spenc.es/writing/email-as-a-commenting-system/" rel="nofollow noreferrer">https://spenc.es/writing/email-as-a-commenting-system/</a><p>Thanks for reading!
Show HN: My related-posts finder script (with LLM and GPT4 enhancement)
I've open-sourced the script I use to find related blog posts (and to describe <i>why</i> they're similar).<p>Works on any set of markdown articles, so should fit into any SSG workflow.<p>Uses embeddings to calculate the similarities, and GPT4 to add descriptive text.
Show HN: My related-posts finder script (with LLM and GPT4 enhancement)
I've open-sourced the script I use to find related blog posts (and to describe <i>why</i> they're similar).<p>Works on any set of markdown articles, so should fit into any SSG workflow.<p>Uses embeddings to calculate the similarities, and GPT4 to add descriptive text.
Show HN: Homebrew 16bit CPU from 74HC logic with C compiler and Unix-like OS
This is a 16bit CPU+Minicomputer from pure 74 series logic. It has user/kernel modes, virtual memory, prioritized IRQ's and DMA. It has a full C compiler and a unix-like OS. It's still in development.
Show HN: Homebrew 16bit CPU from 74HC logic with C compiler and Unix-like OS
This is a 16bit CPU+Minicomputer from pure 74 series logic. It has user/kernel modes, virtual memory, prioritized IRQ's and DMA. It has a full C compiler and a unix-like OS. It's still in development.
Show HN: WarpBuild – x86-64 and arm GitHub Action runners for 30% faster builds
Hey HN, I’m Surya and I’m excited to show you WarpBuild!<p>WarpBuild provides fast, secure `x86-64` and `arm64` Github actions runners. This speeds up your workloads by 30%, at half the cost, and takes ~2mins to get started.<p>We’ve been seeing pretty good results since we opened up signups a week ago and I’ve shared some numbers publicly here [1].<p>Currently, we support linux runners for Github organizations (not personal accounts) and MacOS support is coming soon (~Jan).<p>The way the runners work is deceptively simple:
Runners are assigned to hardware that is ideal for build workloads with fast NVMe disks and high single-core performance.<p>The runners are allocated on VMs, not containers. This provides faster performance and enables use cases requiring (1) nested virtualization for running firecracker and other hypervisors, (2) k8s without relying on kind, and (3) Android emulators on `arm64` instances in test workflows.<p>We also have released a Github Action called `Action-Debugger` that allows you to SSH into a running workflow for simplifying pesky debugging[2].<p>The same set of packages that you’d get on Github hosted runners are pre-configured (on x86-64 runners) so everything works out of the box with no modifications needed.<p>A very minor detail that I’m rather proud of, and I’d love your thoughts on improving it further, is the onboarding flow for the ease of moving workflows to WarpBuild. We’ve also put in a lot of effort into making the workflow start up time where we are as fast or faster than Github.<p>[1] <a href="https://x.com/suryaoruganti/status/1732932591001735419" rel="nofollow noreferrer">https://x.com/suryaoruganti/status/1732932591001735419</a>
[2] <a href="https://github.com/WarpBuilds/action-debugger">https://github.com/WarpBuilds/action-debugger</a>, h/t to tmate<p>Making builds faster by providing optimal hardware and configurations across CI providers is the first step in our mission to make build engineering better.<p>I’d love your feedback on the product and thoughts on other CI pain points we could solve to enable better collaboration and developer experience.
Show HN: WarpBuild – x86-64 and arm GitHub Action runners for 30% faster builds
Hey HN, I’m Surya and I’m excited to show you WarpBuild!<p>WarpBuild provides fast, secure `x86-64` and `arm64` Github actions runners. This speeds up your workloads by 30%, at half the cost, and takes ~2mins to get started.<p>We’ve been seeing pretty good results since we opened up signups a week ago and I’ve shared some numbers publicly here [1].<p>Currently, we support linux runners for Github organizations (not personal accounts) and MacOS support is coming soon (~Jan).<p>The way the runners work is deceptively simple:
Runners are assigned to hardware that is ideal for build workloads with fast NVMe disks and high single-core performance.<p>The runners are allocated on VMs, not containers. This provides faster performance and enables use cases requiring (1) nested virtualization for running firecracker and other hypervisors, (2) k8s without relying on kind, and (3) Android emulators on `arm64` instances in test workflows.<p>We also have released a Github Action called `Action-Debugger` that allows you to SSH into a running workflow for simplifying pesky debugging[2].<p>The same set of packages that you’d get on Github hosted runners are pre-configured (on x86-64 runners) so everything works out of the box with no modifications needed.<p>A very minor detail that I’m rather proud of, and I’d love your thoughts on improving it further, is the onboarding flow for the ease of moving workflows to WarpBuild. We’ve also put in a lot of effort into making the workflow start up time where we are as fast or faster than Github.<p>[1] <a href="https://x.com/suryaoruganti/status/1732932591001735419" rel="nofollow noreferrer">https://x.com/suryaoruganti/status/1732932591001735419</a>
[2] <a href="https://github.com/WarpBuilds/action-debugger">https://github.com/WarpBuilds/action-debugger</a>, h/t to tmate<p>Making builds faster by providing optimal hardware and configurations across CI providers is the first step in our mission to make build engineering better.<p>I’d love your feedback on the product and thoughts on other CI pain points we could solve to enable better collaboration and developer experience.