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: Llama 3.2 Interpretability with Sparse Autoencoders

I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3].<p>I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback.<p>Cheers<p>[1] <a href="https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html" rel="nofollow">https://transformer-circuits.pub/2024/scaling-monosemanticit...</a><p>[2] <a href="https://arxiv.org/abs/2406.04093" rel="nofollow">https://arxiv.org/abs/2406.04093</a><p>[3] <a href="https://arxiv.org/abs/2408.05147" rel="nofollow">https://arxiv.org/abs/2408.05147</a>

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3].<p>I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback.<p>Cheers<p>[1] <a href="https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html" rel="nofollow">https://transformer-circuits.pub/2024/scaling-monosemanticit...</a><p>[2] <a href="https://arxiv.org/abs/2406.04093" rel="nofollow">https://arxiv.org/abs/2406.04093</a><p>[3] <a href="https://arxiv.org/abs/2408.05147" rel="nofollow">https://arxiv.org/abs/2408.05147</a>

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3].<p>I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback.<p>Cheers<p>[1] <a href="https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html" rel="nofollow">https://transformer-circuits.pub/2024/scaling-monosemanticit...</a><p>[2] <a href="https://arxiv.org/abs/2406.04093" rel="nofollow">https://arxiv.org/abs/2406.04093</a><p>[3] <a href="https://arxiv.org/abs/2408.05147" rel="nofollow">https://arxiv.org/abs/2408.05147</a>

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3].<p>I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback.<p>Cheers<p>[1] <a href="https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html" rel="nofollow">https://transformer-circuits.pub/2024/scaling-monosemanticit...</a><p>[2] <a href="https://arxiv.org/abs/2406.04093" rel="nofollow">https://arxiv.org/abs/2406.04093</a><p>[3] <a href="https://arxiv.org/abs/2408.05147" rel="nofollow">https://arxiv.org/abs/2408.05147</a>

Show HN: Self-Host Next.js in Production

Show HN: Self-Host Next.js in Production

Show HN: Rust library for numerical integration of real-valued functions

Integrate is a fast, small, lightweight Rust library for performing numerical integration of real-valued functions. It is designed to integrate functions, providing a simple and efficient way to approximate definite integrals using various numerical methods.<p>Integrate supports a variety of numerical integration techniques: - Newton-Cotes methods:<p><pre><code> - Rectangle Rule. - Trapezoidal Rule. - Simpson's Rule. - Newton's 3/8 Rule. </code></pre> - Gauss quadrature methods:<p><pre><code> - Gauss-Legendre. - Gauss-Laguerre. - Gauss-Hermite. - Gauss-Chebyshev First Kind. - Gauss-Chebyshev Second Kind. </code></pre> - Adaptive Methods:<p><pre><code> - Adaptive Simpson's method </code></pre> - Romberg’s method.

Show HN: Rust library for numerical integration of real-valued functions

Integrate is a fast, small, lightweight Rust library for performing numerical integration of real-valued functions. It is designed to integrate functions, providing a simple and efficient way to approximate definite integrals using various numerical methods.<p>Integrate supports a variety of numerical integration techniques: - Newton-Cotes methods:<p><pre><code> - Rectangle Rule. - Trapezoidal Rule. - Simpson's Rule. - Newton's 3/8 Rule. </code></pre> - Gauss quadrature methods:<p><pre><code> - Gauss-Legendre. - Gauss-Laguerre. - Gauss-Hermite. - Gauss-Chebyshev First Kind. - Gauss-Chebyshev Second Kind. </code></pre> - Adaptive Methods:<p><pre><code> - Adaptive Simpson's method </code></pre> - Romberg’s method.

Show HN: Autotab – Programmable AI browser for turning web tasks into APIs

Hey HN, we're Alexi and Jonas the co-founders of Autotab (<a href="https://autotab.com">https://autotab.com</a>). Autotab is a chrome-based browser you can teach to do complex tasks, with a simple API for running them from your app or backend.<p>Here is a walkthrough of how it works: <a href="https://youtu.be/63co74JHy1k" rel="nofollow">https://youtu.be/63co74JHy1k</a>, and you can try it for free at <a href="https://autotab.com">https://autotab.com</a> by downloading the app.<p>Why a dedicated editor?<p>The number one blocker we've found in building more flexible, agentic automations is performance quality BY FAR (<a href="https://www.langchain.com/stateofaiagents#barriers-and-challenges" rel="nofollow">https://www.langchain.com/stateofaiagents#barriers-and-chall...</a>). For all the talk of cost, latency, and safety, the fact is most people are still just struggling to get agents to work. The keys to solving reliability are better models, yes, but also intent specification. Even humans don't zero-shot these tasks from a prompt. They need to be shown how to perform them, and then refined with question-asking + feedback over time. It is also quite difficult to formulate complete requirements on the spot from memory.<p>The editor makes it easy to build the specification up as you step through your workflow, while generating successful task trajectories for the model. This is the only way we've been able to get the reliability we need for production use cases.<p>But why build a browser?<p>Autotab started as a Chrome extension (with a Show HN post! <a href="https://news.ycombinator.com/item?id=37943931">https://news.ycombinator.com/item?id=37943931</a>). As we iterated with users, we realized that we needed to focus on creating the control surface for intent specification, and that being stuck in a chrome sidepanel wasn't going to work. We also knew that we needed a level of control for the model that we couldn't get without owning the browser. In Autotab, the browser becomes a canvas on which the user and the model are taking turns showing and explaining the task.<p>Key features:<p>1. Self-healing automations that don't break when sites change<p>2. Dedicated authoring tool that builds memory for the model while defining steps for the automation<p>3. Control flows and deep configurability to keep automations on track, even when navigating complex reasoning tasks<p>4. Works with any website (no site-specific APIs needed)<p>5. Runs securely in the cloud or locally<p>6. Simple REST API + client libraries for Python, Node<p>We'd love to get any early feedback from the HN community, ideas for where you'd like the product to go, or experiences in this space. We will be in the comments for the next few hours to respond!

Show HN: Autotab – Programmable AI browser for turning web tasks into APIs

Hey HN, we're Alexi and Jonas the co-founders of Autotab (<a href="https://autotab.com">https://autotab.com</a>). Autotab is a chrome-based browser you can teach to do complex tasks, with a simple API for running them from your app or backend.<p>Here is a walkthrough of how it works: <a href="https://youtu.be/63co74JHy1k" rel="nofollow">https://youtu.be/63co74JHy1k</a>, and you can try it for free at <a href="https://autotab.com">https://autotab.com</a> by downloading the app.<p>Why a dedicated editor?<p>The number one blocker we've found in building more flexible, agentic automations is performance quality BY FAR (<a href="https://www.langchain.com/stateofaiagents#barriers-and-challenges" rel="nofollow">https://www.langchain.com/stateofaiagents#barriers-and-chall...</a>). For all the talk of cost, latency, and safety, the fact is most people are still just struggling to get agents to work. The keys to solving reliability are better models, yes, but also intent specification. Even humans don't zero-shot these tasks from a prompt. They need to be shown how to perform them, and then refined with question-asking + feedback over time. It is also quite difficult to formulate complete requirements on the spot from memory.<p>The editor makes it easy to build the specification up as you step through your workflow, while generating successful task trajectories for the model. This is the only way we've been able to get the reliability we need for production use cases.<p>But why build a browser?<p>Autotab started as a Chrome extension (with a Show HN post! <a href="https://news.ycombinator.com/item?id=37943931">https://news.ycombinator.com/item?id=37943931</a>). As we iterated with users, we realized that we needed to focus on creating the control surface for intent specification, and that being stuck in a chrome sidepanel wasn't going to work. We also knew that we needed a level of control for the model that we couldn't get without owning the browser. In Autotab, the browser becomes a canvas on which the user and the model are taking turns showing and explaining the task.<p>Key features:<p>1. Self-healing automations that don't break when sites change<p>2. Dedicated authoring tool that builds memory for the model while defining steps for the automation<p>3. Control flows and deep configurability to keep automations on track, even when navigating complex reasoning tasks<p>4. Works with any website (no site-specific APIs needed)<p>5. Runs securely in the cloud or locally<p>6. Simple REST API + client libraries for Python, Node<p>We'd love to get any early feedback from the HN community, ideas for where you'd like the product to go, or experiences in this space. We will be in the comments for the next few hours to respond!

Show HN: Autotab – Programmable AI browser for turning web tasks into APIs

Hey HN, we're Alexi and Jonas the co-founders of Autotab (<a href="https://autotab.com">https://autotab.com</a>). Autotab is a chrome-based browser you can teach to do complex tasks, with a simple API for running them from your app or backend.<p>Here is a walkthrough of how it works: <a href="https://youtu.be/63co74JHy1k" rel="nofollow">https://youtu.be/63co74JHy1k</a>, and you can try it for free at <a href="https://autotab.com">https://autotab.com</a> by downloading the app.<p>Why a dedicated editor?<p>The number one blocker we've found in building more flexible, agentic automations is performance quality BY FAR (<a href="https://www.langchain.com/stateofaiagents#barriers-and-challenges" rel="nofollow">https://www.langchain.com/stateofaiagents#barriers-and-chall...</a>). For all the talk of cost, latency, and safety, the fact is most people are still just struggling to get agents to work. The keys to solving reliability are better models, yes, but also intent specification. Even humans don't zero-shot these tasks from a prompt. They need to be shown how to perform them, and then refined with question-asking + feedback over time. It is also quite difficult to formulate complete requirements on the spot from memory.<p>The editor makes it easy to build the specification up as you step through your workflow, while generating successful task trajectories for the model. This is the only way we've been able to get the reliability we need for production use cases.<p>But why build a browser?<p>Autotab started as a Chrome extension (with a Show HN post! <a href="https://news.ycombinator.com/item?id=37943931">https://news.ycombinator.com/item?id=37943931</a>). As we iterated with users, we realized that we needed to focus on creating the control surface for intent specification, and that being stuck in a chrome sidepanel wasn't going to work. We also knew that we needed a level of control for the model that we couldn't get without owning the browser. In Autotab, the browser becomes a canvas on which the user and the model are taking turns showing and explaining the task.<p>Key features:<p>1. Self-healing automations that don't break when sites change<p>2. Dedicated authoring tool that builds memory for the model while defining steps for the automation<p>3. Control flows and deep configurability to keep automations on track, even when navigating complex reasoning tasks<p>4. Works with any website (no site-specific APIs needed)<p>5. Runs securely in the cloud or locally<p>6. Simple REST API + client libraries for Python, Node<p>We'd love to get any early feedback from the HN community, ideas for where you'd like the product to go, or experiences in this space. We will be in the comments for the next few hours to respond!

Show HN: Autotab – Programmable AI browser for turning web tasks into APIs

Hey HN, we're Alexi and Jonas the co-founders of Autotab (<a href="https://autotab.com">https://autotab.com</a>). Autotab is a chrome-based browser you can teach to do complex tasks, with a simple API for running them from your app or backend.<p>Here is a walkthrough of how it works: <a href="https://youtu.be/63co74JHy1k" rel="nofollow">https://youtu.be/63co74JHy1k</a>, and you can try it for free at <a href="https://autotab.com">https://autotab.com</a> by downloading the app.<p>Why a dedicated editor?<p>The number one blocker we've found in building more flexible, agentic automations is performance quality BY FAR (<a href="https://www.langchain.com/stateofaiagents#barriers-and-challenges" rel="nofollow">https://www.langchain.com/stateofaiagents#barriers-and-chall...</a>). For all the talk of cost, latency, and safety, the fact is most people are still just struggling to get agents to work. The keys to solving reliability are better models, yes, but also intent specification. Even humans don't zero-shot these tasks from a prompt. They need to be shown how to perform them, and then refined with question-asking + feedback over time. It is also quite difficult to formulate complete requirements on the spot from memory.<p>The editor makes it easy to build the specification up as you step through your workflow, while generating successful task trajectories for the model. This is the only way we've been able to get the reliability we need for production use cases.<p>But why build a browser?<p>Autotab started as a Chrome extension (with a Show HN post! <a href="https://news.ycombinator.com/item?id=37943931">https://news.ycombinator.com/item?id=37943931</a>). As we iterated with users, we realized that we needed to focus on creating the control surface for intent specification, and that being stuck in a chrome sidepanel wasn't going to work. We also knew that we needed a level of control for the model that we couldn't get without owning the browser. In Autotab, the browser becomes a canvas on which the user and the model are taking turns showing and explaining the task.<p>Key features:<p>1. Self-healing automations that don't break when sites change<p>2. Dedicated authoring tool that builds memory for the model while defining steps for the automation<p>3. Control flows and deep configurability to keep automations on track, even when navigating complex reasoning tasks<p>4. Works with any website (no site-specific APIs needed)<p>5. Runs securely in the cloud or locally<p>6. Simple REST API + client libraries for Python, Node<p>We'd love to get any early feedback from the HN community, ideas for where you'd like the product to go, or experiences in this space. We will be in the comments for the next few hours to respond!

Show HN: Autotab – Programmable AI browser for turning web tasks into APIs

Hey HN, we're Alexi and Jonas the co-founders of Autotab (<a href="https://autotab.com">https://autotab.com</a>). Autotab is a chrome-based browser you can teach to do complex tasks, with a simple API for running them from your app or backend.<p>Here is a walkthrough of how it works: <a href="https://youtu.be/63co74JHy1k" rel="nofollow">https://youtu.be/63co74JHy1k</a>, and you can try it for free at <a href="https://autotab.com">https://autotab.com</a> by downloading the app.<p>Why a dedicated editor?<p>The number one blocker we've found in building more flexible, agentic automations is performance quality BY FAR (<a href="https://www.langchain.com/stateofaiagents#barriers-and-challenges" rel="nofollow">https://www.langchain.com/stateofaiagents#barriers-and-chall...</a>). For all the talk of cost, latency, and safety, the fact is most people are still just struggling to get agents to work. The keys to solving reliability are better models, yes, but also intent specification. Even humans don't zero-shot these tasks from a prompt. They need to be shown how to perform them, and then refined with question-asking + feedback over time. It is also quite difficult to formulate complete requirements on the spot from memory.<p>The editor makes it easy to build the specification up as you step through your workflow, while generating successful task trajectories for the model. This is the only way we've been able to get the reliability we need for production use cases.<p>But why build a browser?<p>Autotab started as a Chrome extension (with a Show HN post! <a href="https://news.ycombinator.com/item?id=37943931">https://news.ycombinator.com/item?id=37943931</a>). As we iterated with users, we realized that we needed to focus on creating the control surface for intent specification, and that being stuck in a chrome sidepanel wasn't going to work. We also knew that we needed a level of control for the model that we couldn't get without owning the browser. In Autotab, the browser becomes a canvas on which the user and the model are taking turns showing and explaining the task.<p>Key features:<p>1. Self-healing automations that don't break when sites change<p>2. Dedicated authoring tool that builds memory for the model while defining steps for the automation<p>3. Control flows and deep configurability to keep automations on track, even when navigating complex reasoning tasks<p>4. Works with any website (no site-specific APIs needed)<p>5. Runs securely in the cloud or locally<p>6. Simple REST API + client libraries for Python, Node<p>We'd love to get any early feedback from the HN community, ideas for where you'd like the product to go, or experiences in this space. We will be in the comments for the next few hours to respond!

Show HN: Embed an SQLite database in your PostgreSQL table

pglite-fusion is a PostgreSQL extension that allows you to embed SQLite databases into your PostgreSQL tables by enabling the creation of columns with the `SQLITE` type. This means every row in the table can have an embedded SQLite database.<p>In addition to the PostgreSQL `SQLITE` type, pglite-fusion provides the `query_sqlite`` function for querying SQLite databases and the `execute_sqlite` function for updating them. Additional functions are listed in the project’s README.<p>The pglite-fusion extension is written in Rust using the pgrx framework [1].<p>----<p>Implementation Details<p>The PostgreSQL `SQLITE` type is stored as a CBOR-encoded `Vec<u8>`. When a query is made, this `Vec<u8>` is written to a random file in the `/tmp` directory. SQLite then loads the file, performs the query, and returns the result as a table containing a single row with an array of JSON-encoded values.<p>The `execute_sqlite` function follows a similar process. However, instead of returning query results, it returns the contents of the SQLite file (stored in `/tmp`) as a new `SQLITE` instance.<p>[1] <a href="https://github.com/pgcentralfoundation/pgrx">https://github.com/pgcentralfoundation/pgrx</a>

Show HN: Embed an SQLite database in your PostgreSQL table

pglite-fusion is a PostgreSQL extension that allows you to embed SQLite databases into your PostgreSQL tables by enabling the creation of columns with the `SQLITE` type. This means every row in the table can have an embedded SQLite database.<p>In addition to the PostgreSQL `SQLITE` type, pglite-fusion provides the `query_sqlite`` function for querying SQLite databases and the `execute_sqlite` function for updating them. Additional functions are listed in the project’s README.<p>The pglite-fusion extension is written in Rust using the pgrx framework [1].<p>----<p>Implementation Details<p>The PostgreSQL `SQLITE` type is stored as a CBOR-encoded `Vec<u8>`. When a query is made, this `Vec<u8>` is written to a random file in the `/tmp` directory. SQLite then loads the file, performs the query, and returns the result as a table containing a single row with an array of JSON-encoded values.<p>The `execute_sqlite` function follows a similar process. However, instead of returning query results, it returns the contents of the SQLite file (stored in `/tmp`) as a new `SQLITE` instance.<p>[1] <a href="https://github.com/pgcentralfoundation/pgrx">https://github.com/pgcentralfoundation/pgrx</a>

Show HN: Physically accurate black hole simulation using your iPhone camera

Show HN: Physically accurate black hole simulation using your iPhone camera

Show HN: Dumbo – Hono inspired framework for PHP

Hey HN, I last PHP professionally over 15 years ago, and I loved it. I switched to Ruby on Rails, then Node/Go/React/GraphQL as there was a lot more demand for those roles. However, PHP is back!<p>In true JavaScript fashion, I decided to learn PHP again by building a framework to put all the pieces together in my brain.<p>I absolutely love Hono.dev, and decided to base the PHP framework on that. Dumbo isn't intended to compete with Laravel, Symphony or Slim, if anything, it's something people can use in production, but also contribute to and be used as a learning resource for others.

Show HN: Dumbo – Hono inspired framework for PHP

Hey HN, I last PHP professionally over 15 years ago, and I loved it. I switched to Ruby on Rails, then Node/Go/React/GraphQL as there was a lot more demand for those roles. However, PHP is back!<p>In true JavaScript fashion, I decided to learn PHP again by building a framework to put all the pieces together in my brain.<p>I absolutely love Hono.dev, and decided to base the PHP framework on that. Dumbo isn't intended to compete with Laravel, Symphony or Slim, if anything, it's something people can use in production, but also contribute to and be used as a learning resource for others.

Show HN: A dynamic C (Hot reloading) module-based Web Framework