The best Hacker News stories from Show from the past day

from

All Show

from the past*

day week month

with these search terms:

Create follow Go back

Latest posts:

Show HN: Appliku – Deployment PaaS for Python/Django

Hey everyone.<p>I have dedicated 4 years of my life to building a solution for easy deployment of [primarily] Python and Django apps.<p>Think of it as an equivalent of Laravel Forge/Hatchbox but for Python apps.<p>For those who are not familiar – Platform as a service on your cloud or on-prem servers.<p>I have posted here 2 years ago and a lot has changed since then.<p>What's new: - New great and easy to use dashboard - backups for databases - cronjobs - stats resources of servers and apps - tons of stability improvements.

Show HN: Appliku – Deployment PaaS for Python/Django

Hey everyone.<p>I have dedicated 4 years of my life to building a solution for easy deployment of [primarily] Python and Django apps.<p>Think of it as an equivalent of Laravel Forge/Hatchbox but for Python apps.<p>For those who are not familiar – Platform as a service on your cloud or on-prem servers.<p>I have posted here 2 years ago and a lot has changed since then.<p>What's new: - New great and easy to use dashboard - backups for databases - cronjobs - stats resources of servers and apps - tons of stability improvements.

Hacker News in Slow Italian

There are plenty of podcasts to listen to some slow basic Italian, but often they just talk about random things I'm not that interested in. Nothing a few hours of tinkering with Python cannot solve these days!<p>Introducing Hacker News in Slow Italian. Each episode is generated automatically, using GPT4 API to summarise the top articles on Hacker News and then fed to Play.ht for text-to-speech.<p>The (very short) code is available on Github: <a href="https://github.com/laky/hn-slow-italian">https://github.com/laky/hn-slow-italian</a>

Show HN: HN Follow – Follow Your Friends on HN

HN Follow lets you follow authors on Hacker News, and get email notifications when they post. It was inspired by alerthn.com and hnreplies.com.<p>The app was built in an experimental style on Val Town. We’re trying to create a new web primitive that you can:<p>1. write like a function 2. run like a script 3. fork like a repo 4. install like an app<p>This is our 5th iteration of this same “HN Follow” app. We launched the 3rd version here on Hacker News six months ago[1], but it was very kindly removed from the front page by dang in favor of us launching Val Town itself first, which we did in January[2].<p>We’re trying to strike the right balance between something you can use and install with one click, and something you can infinitely customize. For example, you could fork `@rodrigoTello.hnFollowApp`[3] and change the input parameter from authors to a generic query, like I do here[4] to get notifications whenever “val town” is mentioned on HN. In addition to emailing myself (via `console.email`), I also send a message to our team’s Discord. The possibilities are endless, but it can also be overwhelming. We’re trying to find the balance where we help you navigate the space of possible integrations, without limiting you the way a no-code tool would. We would really appreciate your guys’ feedback and suggestions!<p>[1] - HN Follow, first launch: <a href="https://news.ycombinator.com/item?id=33533830" rel="nofollow">https://news.ycombinator.com/item?id=33533830</a><p>[2] - Val Town launch: <a href="https://news.ycombinator.com/item?id=34343122" rel="nofollow">https://news.ycombinator.com/item?id=34343122</a><p>[3] - `@rodrigotello.hnFollowApp`: <a href="https://www.val.town/v/rodrigotello.hnFollowApp" rel="nofollow">https://www.val.town/v/rodrigotello.hnFollowApp</a><p>[4] - My fork of hnFollow: <a href="https://www.val.town/v/stevekrouse.hnValTown" rel="nofollow">https://www.val.town/v/stevekrouse.hnValTown</a>

Show HN: HN Follow – Follow Your Friends on HN

HN Follow lets you follow authors on Hacker News, and get email notifications when they post. It was inspired by alerthn.com and hnreplies.com.<p>The app was built in an experimental style on Val Town. We’re trying to create a new web primitive that you can:<p>1. write like a function 2. run like a script 3. fork like a repo 4. install like an app<p>This is our 5th iteration of this same “HN Follow” app. We launched the 3rd version here on Hacker News six months ago[1], but it was very kindly removed from the front page by dang in favor of us launching Val Town itself first, which we did in January[2].<p>We’re trying to strike the right balance between something you can use and install with one click, and something you can infinitely customize. For example, you could fork `@rodrigoTello.hnFollowApp`[3] and change the input parameter from authors to a generic query, like I do here[4] to get notifications whenever “val town” is mentioned on HN. In addition to emailing myself (via `console.email`), I also send a message to our team’s Discord. The possibilities are endless, but it can also be overwhelming. We’re trying to find the balance where we help you navigate the space of possible integrations, without limiting you the way a no-code tool would. We would really appreciate your guys’ feedback and suggestions!<p>[1] - HN Follow, first launch: <a href="https://news.ycombinator.com/item?id=33533830" rel="nofollow">https://news.ycombinator.com/item?id=33533830</a><p>[2] - Val Town launch: <a href="https://news.ycombinator.com/item?id=34343122" rel="nofollow">https://news.ycombinator.com/item?id=34343122</a><p>[3] - `@rodrigotello.hnFollowApp`: <a href="https://www.val.town/v/rodrigotello.hnFollowApp" rel="nofollow">https://www.val.town/v/rodrigotello.hnFollowApp</a><p>[4] - My fork of hnFollow: <a href="https://www.val.town/v/stevekrouse.hnValTown" rel="nofollow">https://www.val.town/v/stevekrouse.hnValTown</a>

Show HN: HN Follow – Follow Your Friends on HN

HN Follow lets you follow authors on Hacker News, and get email notifications when they post. It was inspired by alerthn.com and hnreplies.com.<p>The app was built in an experimental style on Val Town. We’re trying to create a new web primitive that you can:<p>1. write like a function 2. run like a script 3. fork like a repo 4. install like an app<p>This is our 5th iteration of this same “HN Follow” app. We launched the 3rd version here on Hacker News six months ago[1], but it was very kindly removed from the front page by dang in favor of us launching Val Town itself first, which we did in January[2].<p>We’re trying to strike the right balance between something you can use and install with one click, and something you can infinitely customize. For example, you could fork `@rodrigoTello.hnFollowApp`[3] and change the input parameter from authors to a generic query, like I do here[4] to get notifications whenever “val town” is mentioned on HN. In addition to emailing myself (via `console.email`), I also send a message to our team’s Discord. The possibilities are endless, but it can also be overwhelming. We’re trying to find the balance where we help you navigate the space of possible integrations, without limiting you the way a no-code tool would. We would really appreciate your guys’ feedback and suggestions!<p>[1] - HN Follow, first launch: <a href="https://news.ycombinator.com/item?id=33533830" rel="nofollow">https://news.ycombinator.com/item?id=33533830</a><p>[2] - Val Town launch: <a href="https://news.ycombinator.com/item?id=34343122" rel="nofollow">https://news.ycombinator.com/item?id=34343122</a><p>[3] - `@rodrigotello.hnFollowApp`: <a href="https://www.val.town/v/rodrigotello.hnFollowApp" rel="nofollow">https://www.val.town/v/rodrigotello.hnFollowApp</a><p>[4] - My fork of hnFollow: <a href="https://www.val.town/v/stevekrouse.hnValTown" rel="nofollow">https://www.val.town/v/stevekrouse.hnValTown</a>

Show HN: HN Follow – Follow Your Friends on HN

HN Follow lets you follow authors on Hacker News, and get email notifications when they post. It was inspired by alerthn.com and hnreplies.com.<p>The app was built in an experimental style on Val Town. We’re trying to create a new web primitive that you can:<p>1. write like a function 2. run like a script 3. fork like a repo 4. install like an app<p>This is our 5th iteration of this same “HN Follow” app. We launched the 3rd version here on Hacker News six months ago[1], but it was very kindly removed from the front page by dang in favor of us launching Val Town itself first, which we did in January[2].<p>We’re trying to strike the right balance between something you can use and install with one click, and something you can infinitely customize. For example, you could fork `@rodrigoTello.hnFollowApp`[3] and change the input parameter from authors to a generic query, like I do here[4] to get notifications whenever “val town” is mentioned on HN. In addition to emailing myself (via `console.email`), I also send a message to our team’s Discord. The possibilities are endless, but it can also be overwhelming. We’re trying to find the balance where we help you navigate the space of possible integrations, without limiting you the way a no-code tool would. We would really appreciate your guys’ feedback and suggestions!<p>[1] - HN Follow, first launch: <a href="https://news.ycombinator.com/item?id=33533830" rel="nofollow">https://news.ycombinator.com/item?id=33533830</a><p>[2] - Val Town launch: <a href="https://news.ycombinator.com/item?id=34343122" rel="nofollow">https://news.ycombinator.com/item?id=34343122</a><p>[3] - `@rodrigotello.hnFollowApp`: <a href="https://www.val.town/v/rodrigotello.hnFollowApp" rel="nofollow">https://www.val.town/v/rodrigotello.hnFollowApp</a><p>[4] - My fork of hnFollow: <a href="https://www.val.town/v/stevekrouse.hnValTown" rel="nofollow">https://www.val.town/v/stevekrouse.hnValTown</a>

Show HN: Visual intuitive explanations of LLM concepts (LLM University)

Hi HN,<p>We've just published a lot of original, visual, and intuitive explanations of concepts to introduce people to large language models.<p>It's available for free with no sign-up needed and it includes text articles, some video explanations, and code examples/notebooks as well. And we're available to answer your questions in a dedicated Discord channel.<p>You can find it here: https://llm.university/<p>Having written https://jalammar.github.io/illustrated-transformer/, I've been thinking about these topics and how best to communicate them for half a decade. But this project is extra special to me because I got to collaborate on it with two of who I think of as some of the best ML educators out there. Luis Serrano of https://www.youtube.com/@SerranoAcademy and Meor Amer, author of "A Visual Introduction to Deep Learning" https://kdimensions.gumroad.com/l/visualdl<p>We're planning to roll out more content to it (let us know what concepts interest you). But as of now, it has the following structure (With some links for highlighted articles for you to audit):<p>---<p>Module 1: What are Large Language Models<p>- Text Embeddings (https://docs.cohere.com/docs/text-embeddings)<p>- Similarity between words and sentences (https://docs.cohere.com/docs/similarity-between-words-and-sentences)<p>- The attention mechanism<p>- Transformer models (https://docs.cohere.com/docs/transformer-models HN Discussion: https://news.ycombinator.com/item?id=35576918)<p>- Semantic search<p>---<p>Module 2: Text representation<p>- Classification models (https://docs.cohere.com/docs/classification-models)<p>- Classification Evaluation metrics (https://docs.cohere.com/docs/evaluation-metrics)<p>- Classification / Embedding API endpoints<p>- Semantic search<p>- Text clustering<p>- Topic modeling (goes over clustering Ask HN posts https://docs.cohere.com/docs/clustering-hacker-news-posts)<p>- Multilingual semantic search<p>- Multilingual sentiment analysis<p>---<p>Module 3: Text generation<p>- Prompt engineering (https://docs.cohere.com/docs/model-prompting)<p>- Use case ideation<p>- Chaining prompts<p>---<p>A lot of the content originates from common questions we get from users of the LLMs we serve at Cohere. So the focus is more on application of LLMs than theory or training LLMs.<p>Hope you enjoy it, open to all feedback and suggestions!

Show HN: Visual intuitive explanations of LLM concepts (LLM University)

Hi HN,<p>We've just published a lot of original, visual, and intuitive explanations of concepts to introduce people to large language models.<p>It's available for free with no sign-up needed and it includes text articles, some video explanations, and code examples/notebooks as well. And we're available to answer your questions in a dedicated Discord channel.<p>You can find it here: https://llm.university/<p>Having written https://jalammar.github.io/illustrated-transformer/, I've been thinking about these topics and how best to communicate them for half a decade. But this project is extra special to me because I got to collaborate on it with two of who I think of as some of the best ML educators out there. Luis Serrano of https://www.youtube.com/@SerranoAcademy and Meor Amer, author of "A Visual Introduction to Deep Learning" https://kdimensions.gumroad.com/l/visualdl<p>We're planning to roll out more content to it (let us know what concepts interest you). But as of now, it has the following structure (With some links for highlighted articles for you to audit):<p>---<p>Module 1: What are Large Language Models<p>- Text Embeddings (https://docs.cohere.com/docs/text-embeddings)<p>- Similarity between words and sentences (https://docs.cohere.com/docs/similarity-between-words-and-sentences)<p>- The attention mechanism<p>- Transformer models (https://docs.cohere.com/docs/transformer-models HN Discussion: https://news.ycombinator.com/item?id=35576918)<p>- Semantic search<p>---<p>Module 2: Text representation<p>- Classification models (https://docs.cohere.com/docs/classification-models)<p>- Classification Evaluation metrics (https://docs.cohere.com/docs/evaluation-metrics)<p>- Classification / Embedding API endpoints<p>- Semantic search<p>- Text clustering<p>- Topic modeling (goes over clustering Ask HN posts https://docs.cohere.com/docs/clustering-hacker-news-posts)<p>- Multilingual semantic search<p>- Multilingual sentiment analysis<p>---<p>Module 3: Text generation<p>- Prompt engineering (https://docs.cohere.com/docs/model-prompting)<p>- Use case ideation<p>- Chaining prompts<p>---<p>A lot of the content originates from common questions we get from users of the LLMs we serve at Cohere. So the focus is more on application of LLMs than theory or training LLMs.<p>Hope you enjoy it, open to all feedback and suggestions!

Show HN: Visual intuitive explanations of LLM concepts (LLM University)

Hi HN,<p>We've just published a lot of original, visual, and intuitive explanations of concepts to introduce people to large language models.<p>It's available for free with no sign-up needed and it includes text articles, some video explanations, and code examples/notebooks as well. And we're available to answer your questions in a dedicated Discord channel.<p>You can find it here: https://llm.university/<p>Having written https://jalammar.github.io/illustrated-transformer/, I've been thinking about these topics and how best to communicate them for half a decade. But this project is extra special to me because I got to collaborate on it with two of who I think of as some of the best ML educators out there. Luis Serrano of https://www.youtube.com/@SerranoAcademy and Meor Amer, author of "A Visual Introduction to Deep Learning" https://kdimensions.gumroad.com/l/visualdl<p>We're planning to roll out more content to it (let us know what concepts interest you). But as of now, it has the following structure (With some links for highlighted articles for you to audit):<p>---<p>Module 1: What are Large Language Models<p>- Text Embeddings (https://docs.cohere.com/docs/text-embeddings)<p>- Similarity between words and sentences (https://docs.cohere.com/docs/similarity-between-words-and-sentences)<p>- The attention mechanism<p>- Transformer models (https://docs.cohere.com/docs/transformer-models HN Discussion: https://news.ycombinator.com/item?id=35576918)<p>- Semantic search<p>---<p>Module 2: Text representation<p>- Classification models (https://docs.cohere.com/docs/classification-models)<p>- Classification Evaluation metrics (https://docs.cohere.com/docs/evaluation-metrics)<p>- Classification / Embedding API endpoints<p>- Semantic search<p>- Text clustering<p>- Topic modeling (goes over clustering Ask HN posts https://docs.cohere.com/docs/clustering-hacker-news-posts)<p>- Multilingual semantic search<p>- Multilingual sentiment analysis<p>---<p>Module 3: Text generation<p>- Prompt engineering (https://docs.cohere.com/docs/model-prompting)<p>- Use case ideation<p>- Chaining prompts<p>---<p>A lot of the content originates from common questions we get from users of the LLMs we serve at Cohere. So the focus is more on application of LLMs than theory or training LLMs.<p>Hope you enjoy it, open to all feedback and suggestions!

Show HN: Visual intuitive explanations of LLM concepts (LLM University)

Hi HN,<p>We've just published a lot of original, visual, and intuitive explanations of concepts to introduce people to large language models.<p>It's available for free with no sign-up needed and it includes text articles, some video explanations, and code examples/notebooks as well. And we're available to answer your questions in a dedicated Discord channel.<p>You can find it here: https://llm.university/<p>Having written https://jalammar.github.io/illustrated-transformer/, I've been thinking about these topics and how best to communicate them for half a decade. But this project is extra special to me because I got to collaborate on it with two of who I think of as some of the best ML educators out there. Luis Serrano of https://www.youtube.com/@SerranoAcademy and Meor Amer, author of "A Visual Introduction to Deep Learning" https://kdimensions.gumroad.com/l/visualdl<p>We're planning to roll out more content to it (let us know what concepts interest you). But as of now, it has the following structure (With some links for highlighted articles for you to audit):<p>---<p>Module 1: What are Large Language Models<p>- Text Embeddings (https://docs.cohere.com/docs/text-embeddings)<p>- Similarity between words and sentences (https://docs.cohere.com/docs/similarity-between-words-and-sentences)<p>- The attention mechanism<p>- Transformer models (https://docs.cohere.com/docs/transformer-models HN Discussion: https://news.ycombinator.com/item?id=35576918)<p>- Semantic search<p>---<p>Module 2: Text representation<p>- Classification models (https://docs.cohere.com/docs/classification-models)<p>- Classification Evaluation metrics (https://docs.cohere.com/docs/evaluation-metrics)<p>- Classification / Embedding API endpoints<p>- Semantic search<p>- Text clustering<p>- Topic modeling (goes over clustering Ask HN posts https://docs.cohere.com/docs/clustering-hacker-news-posts)<p>- Multilingual semantic search<p>- Multilingual sentiment analysis<p>---<p>Module 3: Text generation<p>- Prompt engineering (https://docs.cohere.com/docs/model-prompting)<p>- Use case ideation<p>- Chaining prompts<p>---<p>A lot of the content originates from common questions we get from users of the LLMs we serve at Cohere. So the focus is more on application of LLMs than theory or training LLMs.<p>Hope you enjoy it, open to all feedback and suggestions!

Show HN: Aimless.js – the missing js randomness library

Show HN: Gis.chat – a Geospatial Community

Hi folks! I'm excited to show you gis.chat, a geospatial chat platform in both senses: a platform about geospatial topics and a geospatial platform itself, referencing the location of our communities.<p>The setup is fairly simple and reproducible: a plain Zulip instance and a homepage with geospatial search capabilities.<p>It seems almost trivial but it has some very nice features. I guess you should be familiar with Zulips stream/topic model to follow along (<a href="https://zulip.com/help/streams-and-topics" rel="nofollow">https://zulip.com/help/streams-and-topics</a>).<p>The core idea is that there are city-specific streams (currently represented by a pin), but there could just as well be streams about points of interest, line geometries (e.g. a river) or polygons (e.g. national park).<p>- Every local stream can have the same topics, e.g. "general", "news", "meetups", "jobs" etc. - With Zulip's search you can either search for a particular topic, e.g. "news" in a local stream or instead in all streams and have some kind of news feed of the community with "topic:news" - Once more communities are added, specific filters could be added, e.g. country-wise or by drawing your own area of interest - Eventually, for the ones who like, users could associate themselves with a local community in their profile or add there main location so one could not only search for the local communities but instead also for individuals<p>There are many nice features in Zulip's pipeline that would foster gis.chat:<p>- Further nesting of streams/topics - Semantic search<p>If for example Zulip would allow for saving coordinates (or better an entire geometry) in the Postgres DB, with the help of PostGIS, Zulip's search could allow for bounding boxes (or custom geometries).<p>Let me know if you have any kind of other ideas or feedback!

Show HN: Gis.chat – a Geospatial Community

Hi folks! I'm excited to show you gis.chat, a geospatial chat platform in both senses: a platform about geospatial topics and a geospatial platform itself, referencing the location of our communities.<p>The setup is fairly simple and reproducible: a plain Zulip instance and a homepage with geospatial search capabilities.<p>It seems almost trivial but it has some very nice features. I guess you should be familiar with Zulips stream/topic model to follow along (<a href="https://zulip.com/help/streams-and-topics" rel="nofollow">https://zulip.com/help/streams-and-topics</a>).<p>The core idea is that there are city-specific streams (currently represented by a pin), but there could just as well be streams about points of interest, line geometries (e.g. a river) or polygons (e.g. national park).<p>- Every local stream can have the same topics, e.g. "general", "news", "meetups", "jobs" etc. - With Zulip's search you can either search for a particular topic, e.g. "news" in a local stream or instead in all streams and have some kind of news feed of the community with "topic:news" - Once more communities are added, specific filters could be added, e.g. country-wise or by drawing your own area of interest - Eventually, for the ones who like, users could associate themselves with a local community in their profile or add there main location so one could not only search for the local communities but instead also for individuals<p>There are many nice features in Zulip's pipeline that would foster gis.chat:<p>- Further nesting of streams/topics - Semantic search<p>If for example Zulip would allow for saving coordinates (or better an entire geometry) in the Postgres DB, with the help of PostGIS, Zulip's search could allow for bounding boxes (or custom geometries).<p>Let me know if you have any kind of other ideas or feedback!

Show HN: Gis.chat – a Geospatial Community

Hi folks! I'm excited to show you gis.chat, a geospatial chat platform in both senses: a platform about geospatial topics and a geospatial platform itself, referencing the location of our communities.<p>The setup is fairly simple and reproducible: a plain Zulip instance and a homepage with geospatial search capabilities.<p>It seems almost trivial but it has some very nice features. I guess you should be familiar with Zulips stream/topic model to follow along (<a href="https://zulip.com/help/streams-and-topics" rel="nofollow">https://zulip.com/help/streams-and-topics</a>).<p>The core idea is that there are city-specific streams (currently represented by a pin), but there could just as well be streams about points of interest, line geometries (e.g. a river) or polygons (e.g. national park).<p>- Every local stream can have the same topics, e.g. "general", "news", "meetups", "jobs" etc. - With Zulip's search you can either search for a particular topic, e.g. "news" in a local stream or instead in all streams and have some kind of news feed of the community with "topic:news" - Once more communities are added, specific filters could be added, e.g. country-wise or by drawing your own area of interest - Eventually, for the ones who like, users could associate themselves with a local community in their profile or add there main location so one could not only search for the local communities but instead also for individuals<p>There are many nice features in Zulip's pipeline that would foster gis.chat:<p>- Further nesting of streams/topics - Semantic search<p>If for example Zulip would allow for saving coordinates (or better an entire geometry) in the Postgres DB, with the help of PostGIS, Zulip's search could allow for bounding boxes (or custom geometries).<p>Let me know if you have any kind of other ideas or feedback!

Show HN: Honda Civic Infotainment Reverse-Engineering

I own a 2021 Honda Civic and have been annoyed by the lack of public documentation/hacking tools for the Android-based headunit. I hope to address this by publishing my research into the headunit and encouraging discussion and community contribution

Show HN: Honda Civic Infotainment Reverse-Engineering

I own a 2021 Honda Civic and have been annoyed by the lack of public documentation/hacking tools for the Android-based headunit. I hope to address this by publishing my research into the headunit and encouraging discussion and community contribution

Show HN: HelpHub – GPT chatbot for any site

Hi HN,<p>I’m the founder of a SaaS platform called CommandBar (YC S20). We’ve been mucking around with AI-related side quests for a while, but recently got excited enough about one to test it with some customers. Results were surprisingly good so we decided to launch it.<p>HelpHub is AI chat + semantic search for any website or web app.<p>You can add source content in 3 ways: -Crawling any public site via a URL (e.g. your marketing site or blog) -Syncing with a CMS (like Zendesk or Intercom) -Add content manually<p>The chatbot is then “trained” on that content and will answer question’s based on that content only, not referencing directly the knowledge.<p>The output is an embeddable widget the contains two things: the chatbot interface for user’s to ask questions, and a search interface for users to search through the content the bot is trained on directly (as well as view source content).<p>You can play around with a demo on some popular sites here: <a href="https://helphub.commandbar.com">https://helphub.commandbar.com</a><p>Some features we added that make it better IMO than just chat: -Suggested questions (based on the page the user is on and their chat history) -Suggested follow-up questions in a chat response -Ask a question about a specific doc -Recommend content based on who the user is and where they are<p>Would love to hear feedback (not lost on me that there are other chatgpt-for-your-site products and we are probably missing a ton of functionality from there) and can also share details about how we built this. It’s not rocket science but does feel magic :)<p>-James

Show HN: HelpHub – GPT chatbot for any site

Hi HN,<p>I’m the founder of a SaaS platform called CommandBar (YC S20). We’ve been mucking around with AI-related side quests for a while, but recently got excited enough about one to test it with some customers. Results were surprisingly good so we decided to launch it.<p>HelpHub is AI chat + semantic search for any website or web app.<p>You can add source content in 3 ways: -Crawling any public site via a URL (e.g. your marketing site or blog) -Syncing with a CMS (like Zendesk or Intercom) -Add content manually<p>The chatbot is then “trained” on that content and will answer question’s based on that content only, not referencing directly the knowledge.<p>The output is an embeddable widget the contains two things: the chatbot interface for user’s to ask questions, and a search interface for users to search through the content the bot is trained on directly (as well as view source content).<p>You can play around with a demo on some popular sites here: <a href="https://helphub.commandbar.com">https://helphub.commandbar.com</a><p>Some features we added that make it better IMO than just chat: -Suggested questions (based on the page the user is on and their chat history) -Suggested follow-up questions in a chat response -Ask a question about a specific doc -Recommend content based on who the user is and where they are<p>Would love to hear feedback (not lost on me that there are other chatgpt-for-your-site products and we are probably missing a ton of functionality from there) and can also share details about how we built this. It’s not rocket science but does feel magic :)<p>-James

Show HN: Image background removal without annoying subscriptions

Hi HN,<p>Removing the background from images is a surprisingly common image processing task, and AI has made it really easy. The technology has come a long way since segment leader remove.bg launched here on hn in Dec 2018 [1]. Chasing remove.bg's success, a legion of providers have come on the market offering varying levels of quality & service.<p>Despite there being a large number of competing services, most still price for very high (~95%?) gross margins. Furthermore, subscriptions make the effective unit price a lot higher than the list price for infrequent users, and requires effort & attention to ensure you're getting value for money. This has prevented a host of use cases (e.g. infrequent professional / hobbyist) and business models (e.g. ad-supported websites & mobile apps).<p>We see this as an opportunity where we can jump to the market's logical conclusion to gain market share and build goodwill: cost-plus PAYGO pricing, i.e. the "S3 pricing model".<p>So we've built yet-another image background removal service ( <a href="https://pixian.ai" rel="nofollow">https://pixian.ai</a> - introductory post 6 months ago [2], a ton has been improved since then) but with a couple of twists:<p>1. Quantified quality comparison (90-120% of remove.bg, depending on image category), free for you to check your own images so you can make an informed choice.<p>2. Customer-friendly pricing (PAYGO @ 1-10% of competitors' subscriptions) with a generous free tier (and free while in beta).<p>3. A novel API result format: Delta PNG [3], which offers excellent latency & bandwidth savings. Especially useful for mobile apps.<p>4. Operational transparency: actual volume & latency metrics public, with more coming soon (all API providers should be showing this).<p>There's of course more to it than just price and we see several sources of differentiation in this market: quality, price, capability, reliability, latency, and goodwill.<p>As a new entrant we're looking to meet-or-beat the quality bar; beat on price, capability, reliability and latency; and to build up goodwill over time.<p>Our goal is to make it a no-brainer for new accounts to choose us, and to provide the tools and guidance necessary for existing accounts to make the switch with confidence.<p>We'd love for you to try it out and to hear your thoughts!<p><a href="https://pixian.ai" rel="nofollow">https://pixian.ai</a><p>[1] <a href="https://news.ycombinator.com/item?id=18697601" rel="nofollow">https://news.ycombinator.com/item?id=18697601</a> [2] <a href="https://news.ycombinator.com/item?id=33439405" rel="nofollow">https://news.ycombinator.com/item?id=33439405</a> [3] <a href="https://pixian.ai/api/deltaPng" rel="nofollow">https://pixian.ai/api/deltaPng</a>