The best Hacker News stories from Show from the past day
Latest posts:
Show HN: TypeScript/React/Vue Window Layout Manager (Tabs, Floating, Popouts)
Show HN: TypeScript/React/Vue Window Layout Manager (Tabs, Floating, Popouts)
Show HN: TypeScript/React/Vue Window Layout Manager (Tabs, Floating, Popouts)
Show HN: Freeact – A Lightweight Library for Code-Action Based Agents
Hello! We just released freeact (<a href="https://github.com/gradion-ai/freeact">https://github.com/gradion-ai/freeact</a>), a lightweight agent library that empowers language models to act as autonomous agents through executable code actions.<p>By enabling agents to express their actions directly in code rather than through constrained formats like JSON, freeact provides a flexible and powerful approach to solving complex, open-ended problems that require dynamic solution paths.<p>* Supports dynamic installation and utilization of Python packages at runtime<p>* Agents learn from feedback and store successful code actions as reusable skills in long-term memory<p>* Skills can be interactively developed and refined in collaboration with freeact agents<p>* Agents compose skills and any other Python modules to build increasingly sophisticated capabilities<p>* Code actions are executed in ipybox (<a href="https://github.com/gradion-ai/ipybox">https://github.com/gradion-ai/ipybox</a>), a secure Docker + IPython sandbox that runs locally or remotely<p>GitHub repo: <a href="https://github.com/gradion-ai/freeact">https://github.com/gradion-ai/freeact</a><p>Evaluation: <a href="https://gradion-ai.github.io/freeact/evaluation/" rel="nofollow">https://gradion-ai.github.io/freeact/evaluation/</a><p>See it in action: <a href="https://github.com/user-attachments/assets/83cec179-54dc-456c-b647-ea98ec99600b">https://github.com/user-attachments/assets/83cec179-54dc-456...</a><p>We'd love to hear your feedback!
Show HN: Boulette - Protect you from yourself (even as root).
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features.<p>The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license: <a href="https://github.com/PriorLabs/tabpfn">https://github.com/PriorLabs/tabpfn</a>. You can also try it via API: <a href="https://github.com/PriorLabs/tabpfn-client">https://github.com/PriorLabs/tabpfn-client</a><p>TabPFN v2 is trained on 130 million synthetic tabular prediction datasets to perform in-context learning and output a predictive distribution for the test data points. Each dataset acts as one meta-datapoint to train the TabPFN weights with SGD. As a foundation model, TabPFN allows for fine-tuning, density estimation and data generation.<p>Compared to TabPFN v1, v2 now natively supports categorical features and missing values. TabPFN v2 performs just as well on datasets with or without these. It also handles outliers and uninformative features naturally, problems that often throw off standard neural nets.<p>TabPFN v2 performs as well with half the data as the next best baseline (CatBoost) with all the data.<p>We also compared TabPFN to the SOTA AutoML system AutoGluon 1.0. Standard TabPFN already outperforms AutoGluon on classification and ties on regression, but ensembling multiple TabPFNs in TabPFN v2 (PHE) is even better.<p>There are some limitations: TabPFN v2 is very fast to train and does not require hyperparameter tuning, but inference is slow. The model is also only designed for datasets up to 10k data points and 500 features. While it may perform well on larger datasets, it hasn't been our focus.<p>We're actively working on removing these limitations and intend to release new versions of TabPFN that can handle larger datasets, have faster inference and perform in additional predictive settings such as time-series and recommender systems.<p>We would love for you to try out TabPFN v2 and give us your feedback!
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features.<p>The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license: <a href="https://github.com/PriorLabs/tabpfn">https://github.com/PriorLabs/tabpfn</a>. You can also try it via API: <a href="https://github.com/PriorLabs/tabpfn-client">https://github.com/PriorLabs/tabpfn-client</a><p>TabPFN v2 is trained on 130 million synthetic tabular prediction datasets to perform in-context learning and output a predictive distribution for the test data points. Each dataset acts as one meta-datapoint to train the TabPFN weights with SGD. As a foundation model, TabPFN allows for fine-tuning, density estimation and data generation.<p>Compared to TabPFN v1, v2 now natively supports categorical features and missing values. TabPFN v2 performs just as well on datasets with or without these. It also handles outliers and uninformative features naturally, problems that often throw off standard neural nets.<p>TabPFN v2 performs as well with half the data as the next best baseline (CatBoost) with all the data.<p>We also compared TabPFN to the SOTA AutoML system AutoGluon 1.0. Standard TabPFN already outperforms AutoGluon on classification and ties on regression, but ensembling multiple TabPFNs in TabPFN v2 (PHE) is even better.<p>There are some limitations: TabPFN v2 is very fast to train and does not require hyperparameter tuning, but inference is slow. The model is also only designed for datasets up to 10k data points and 500 features. While it may perform well on larger datasets, it hasn't been our focus.<p>We're actively working on removing these limitations and intend to release new versions of TabPFN that can handle larger datasets, have faster inference and perform in additional predictive settings such as time-series and recommender systems.<p>We would love for you to try out TabPFN v2 and give us your feedback!
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features.<p>The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license: <a href="https://github.com/PriorLabs/tabpfn">https://github.com/PriorLabs/tabpfn</a>. You can also try it via API: <a href="https://github.com/PriorLabs/tabpfn-client">https://github.com/PriorLabs/tabpfn-client</a><p>TabPFN v2 is trained on 130 million synthetic tabular prediction datasets to perform in-context learning and output a predictive distribution for the test data points. Each dataset acts as one meta-datapoint to train the TabPFN weights with SGD. As a foundation model, TabPFN allows for fine-tuning, density estimation and data generation.<p>Compared to TabPFN v1, v2 now natively supports categorical features and missing values. TabPFN v2 performs just as well on datasets with or without these. It also handles outliers and uninformative features naturally, problems that often throw off standard neural nets.<p>TabPFN v2 performs as well with half the data as the next best baseline (CatBoost) with all the data.<p>We also compared TabPFN to the SOTA AutoML system AutoGluon 1.0. Standard TabPFN already outperforms AutoGluon on classification and ties on regression, but ensembling multiple TabPFNs in TabPFN v2 (PHE) is even better.<p>There are some limitations: TabPFN v2 is very fast to train and does not require hyperparameter tuning, but inference is slow. The model is also only designed for datasets up to 10k data points and 500 features. While it may perform well on larger datasets, it hasn't been our focus.<p>We're actively working on removing these limitations and intend to release new versions of TabPFN that can handle larger datasets, have faster inference and perform in additional predictive settings such as time-series and recommender systems.<p>We would love for you to try out TabPFN v2 and give us your feedback!
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features.<p>The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license: <a href="https://github.com/PriorLabs/tabpfn">https://github.com/PriorLabs/tabpfn</a>. You can also try it via API: <a href="https://github.com/PriorLabs/tabpfn-client">https://github.com/PriorLabs/tabpfn-client</a><p>TabPFN v2 is trained on 130 million synthetic tabular prediction datasets to perform in-context learning and output a predictive distribution for the test data points. Each dataset acts as one meta-datapoint to train the TabPFN weights with SGD. As a foundation model, TabPFN allows for fine-tuning, density estimation and data generation.<p>Compared to TabPFN v1, v2 now natively supports categorical features and missing values. TabPFN v2 performs just as well on datasets with or without these. It also handles outliers and uninformative features naturally, problems that often throw off standard neural nets.<p>TabPFN v2 performs as well with half the data as the next best baseline (CatBoost) with all the data.<p>We also compared TabPFN to the SOTA AutoML system AutoGluon 1.0. Standard TabPFN already outperforms AutoGluon on classification and ties on regression, but ensembling multiple TabPFNs in TabPFN v2 (PHE) is even better.<p>There are some limitations: TabPFN v2 is very fast to train and does not require hyperparameter tuning, but inference is slow. The model is also only designed for datasets up to 10k data points and 500 features. While it may perform well on larger datasets, it hasn't been our focus.<p>We're actively working on removing these limitations and intend to release new versions of TabPFN that can handle larger datasets, have faster inference and perform in additional predictive settings such as time-series and recommender systems.<p>We would love for you to try out TabPFN v2 and give us your feedback!
Show HN: LA Wildfire Satellite Analysis
Show HN: LA Wildfire Satellite Analysis
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Kate's App
Caregiving is a natural, human act of compassion and caring, and most of us, at some point, will rely on someone to help us with our health care (> 70%) or be tasked with helping someone else (> 10%).<p>Kate's App is a tool to coordinate doctor contact information, prescriptions, pharmacies, appointments, notes, and other information with family and caregivers, and do it safely and privately. This is not a clinic portal, and is not associated with any insurance or medical providers.<p>The app is 95% complete, and is entirely usable as is (for any interested beta users). I intend to clean up the rest of it, and go GA within a few weeks. In the meantime, I would love to answer any questions or hear helpful critiques.<p>BTW, Show HN is the best.
Show HN: Stagehand – an open source browser automation framework powered by AI
Hi HN! I’m Anirudh — longtime lurker, first time poster, and I couldn’t be more excited to show you Stagehand.<p>Stagehand is a TypeScript project that extends Playwright with three simple AI methods — act, extract, and observe. We’d love for you to try it out using the command below:<p><pre><code> npx create-browser-app --example quickstart
</code></pre>
Here’s a sample workflow:<p><pre><code> const stagehand = new Stagehand();
await stagehand.init();
// Stagehand overrides the Playwright Page and Context classes
const { page, context } = stagehand
await page.goto("instadash.com") // Regular Playwright
// Take action on the page
await page.act({ action: "click on taqueria cazadores" })
// Extract relevant data from the page
const { price } = await page.extract({
instruction: "extract the price of the super burrito",
schema: z.object({
price: z.number()
})
})
</code></pre>
We built Stagehand because we loved building browser automations using Playwright and Selenium, but we grew frustrated at how cumbersome it is to just get started and write simple browser automations. These frameworks, while incredibly powerful, are built for QA testing and are thus notoriously prone to fail if there are minor changes in the UI or underlying DOM structure.<p>The goal of Stagehand is twofold:<p>1. Make browser automations easier to write
2. Make browser automations more resilient to DOM changes.<p>We were super energized by what we’ve been seeing with vision-based computer use agents. We think with a browser, you can provide even richer data by leveraging the information in the DOM + a11y tree in addition to what’s rendered on the page. However, we didn’t want to go so far as to build an agent, since we wanted fine-grained control over each step that an agent can take.<p>Therefore, the happy medium we built was to extend the existing powerful functionalities of Playwright with simple and extensible AI APIs that return the decision-making power back to the developer at each step.<p>Check out our docs: <a href="https://docs.stagehand.dev" rel="nofollow">https://docs.stagehand.dev</a><p>We’d love for you to join and give us feedback on Slack as well: <a href="https://stagehand.dev/slack" rel="nofollow">https://stagehand.dev/slack</a>
Show HN: Stagehand – an open source browser automation framework powered by AI
Hi HN! I’m Anirudh — longtime lurker, first time poster, and I couldn’t be more excited to show you Stagehand.<p>Stagehand is a TypeScript project that extends Playwright with three simple AI methods — act, extract, and observe. We’d love for you to try it out using the command below:<p><pre><code> npx create-browser-app --example quickstart
</code></pre>
Here’s a sample workflow:<p><pre><code> const stagehand = new Stagehand();
await stagehand.init();
// Stagehand overrides the Playwright Page and Context classes
const { page, context } = stagehand
await page.goto("instadash.com") // Regular Playwright
// Take action on the page
await page.act({ action: "click on taqueria cazadores" })
// Extract relevant data from the page
const { price } = await page.extract({
instruction: "extract the price of the super burrito",
schema: z.object({
price: z.number()
})
})
</code></pre>
We built Stagehand because we loved building browser automations using Playwright and Selenium, but we grew frustrated at how cumbersome it is to just get started and write simple browser automations. These frameworks, while incredibly powerful, are built for QA testing and are thus notoriously prone to fail if there are minor changes in the UI or underlying DOM structure.<p>The goal of Stagehand is twofold:<p>1. Make browser automations easier to write
2. Make browser automations more resilient to DOM changes.<p>We were super energized by what we’ve been seeing with vision-based computer use agents. We think with a browser, you can provide even richer data by leveraging the information in the DOM + a11y tree in addition to what’s rendered on the page. However, we didn’t want to go so far as to build an agent, since we wanted fine-grained control over each step that an agent can take.<p>Therefore, the happy medium we built was to extend the existing powerful functionalities of Playwright with simple and extensible AI APIs that return the decision-making power back to the developer at each step.<p>Check out our docs: <a href="https://docs.stagehand.dev" rel="nofollow">https://docs.stagehand.dev</a><p>We’d love for you to join and give us feedback on Slack as well: <a href="https://stagehand.dev/slack" rel="nofollow">https://stagehand.dev/slack</a>
Show HN: Stagehand – an open source browser automation framework powered by AI
Hi HN! I’m Anirudh — longtime lurker, first time poster, and I couldn’t be more excited to show you Stagehand.<p>Stagehand is a TypeScript project that extends Playwright with three simple AI methods — act, extract, and observe. We’d love for you to try it out using the command below:<p><pre><code> npx create-browser-app --example quickstart
</code></pre>
Here’s a sample workflow:<p><pre><code> const stagehand = new Stagehand();
await stagehand.init();
// Stagehand overrides the Playwright Page and Context classes
const { page, context } = stagehand
await page.goto("instadash.com") // Regular Playwright
// Take action on the page
await page.act({ action: "click on taqueria cazadores" })
// Extract relevant data from the page
const { price } = await page.extract({
instruction: "extract the price of the super burrito",
schema: z.object({
price: z.number()
})
})
</code></pre>
We built Stagehand because we loved building browser automations using Playwright and Selenium, but we grew frustrated at how cumbersome it is to just get started and write simple browser automations. These frameworks, while incredibly powerful, are built for QA testing and are thus notoriously prone to fail if there are minor changes in the UI or underlying DOM structure.<p>The goal of Stagehand is twofold:<p>1. Make browser automations easier to write
2. Make browser automations more resilient to DOM changes.<p>We were super energized by what we’ve been seeing with vision-based computer use agents. We think with a browser, you can provide even richer data by leveraging the information in the DOM + a11y tree in addition to what’s rendered on the page. However, we didn’t want to go so far as to build an agent, since we wanted fine-grained control over each step that an agent can take.<p>Therefore, the happy medium we built was to extend the existing powerful functionalities of Playwright with simple and extensible AI APIs that return the decision-making power back to the developer at each step.<p>Check out our docs: <a href="https://docs.stagehand.dev" rel="nofollow">https://docs.stagehand.dev</a><p>We’d love for you to join and give us feedback on Slack as well: <a href="https://stagehand.dev/slack" rel="nofollow">https://stagehand.dev/slack</a>