The best Hacker News stories from Show from the past day
Latest posts:
Show HN: GPT-JSON – Structured and typehinted GPT responses in Python
Hey HN, I've been using GPT a lot lately in some side projects around data generation and benchmarking. During the course of prompt tuning I ended up with a pretty complicated request: the value that I was looking for, an explanation, a criticism, etc. JSON was the most natural output format for this but results would often be broken, have wrong types, or contain missing fields.<p>There's been some positive movement in this space, like with jsonformer (<a href="https://github.com/1rgs/jsonformer">https://github.com/1rgs/jsonformer</a>) the other day. But nothing that was plug and play with GPT.<p>This library consolidates the separate logic that I built across 5 different projects. It lets you prompt the model for how it should return fields, inject variable prompts, handle common formatting errors, then cast to pydantic when you're done for typehinting and validation in your IDE. If you're able to play around with it, let me know what you think.
Show HN: GPT-JSON – Structured and typehinted GPT responses in Python
Hey HN, I've been using GPT a lot lately in some side projects around data generation and benchmarking. During the course of prompt tuning I ended up with a pretty complicated request: the value that I was looking for, an explanation, a criticism, etc. JSON was the most natural output format for this but results would often be broken, have wrong types, or contain missing fields.<p>There's been some positive movement in this space, like with jsonformer (<a href="https://github.com/1rgs/jsonformer">https://github.com/1rgs/jsonformer</a>) the other day. But nothing that was plug and play with GPT.<p>This library consolidates the separate logic that I built across 5 different projects. It lets you prompt the model for how it should return fields, inject variable prompts, handle common formatting errors, then cast to pydantic when you're done for typehinting and validation in your IDE. If you're able to play around with it, let me know what you think.
Show HN: GPT-JSON – Structured and typehinted GPT responses in Python
Hey HN, I've been using GPT a lot lately in some side projects around data generation and benchmarking. During the course of prompt tuning I ended up with a pretty complicated request: the value that I was looking for, an explanation, a criticism, etc. JSON was the most natural output format for this but results would often be broken, have wrong types, or contain missing fields.<p>There's been some positive movement in this space, like with jsonformer (<a href="https://github.com/1rgs/jsonformer">https://github.com/1rgs/jsonformer</a>) the other day. But nothing that was plug and play with GPT.<p>This library consolidates the separate logic that I built across 5 different projects. It lets you prompt the model for how it should return fields, inject variable prompts, handle common formatting errors, then cast to pydantic when you're done for typehinting and validation in your IDE. If you're able to play around with it, let me know what you think.
Show HN: GPT-JSON – Structured and typehinted GPT responses in Python
Hey HN, I've been using GPT a lot lately in some side projects around data generation and benchmarking. During the course of prompt tuning I ended up with a pretty complicated request: the value that I was looking for, an explanation, a criticism, etc. JSON was the most natural output format for this but results would often be broken, have wrong types, or contain missing fields.<p>There's been some positive movement in this space, like with jsonformer (<a href="https://github.com/1rgs/jsonformer">https://github.com/1rgs/jsonformer</a>) the other day. But nothing that was plug and play with GPT.<p>This library consolidates the separate logic that I built across 5 different projects. It lets you prompt the model for how it should return fields, inject variable prompts, handle common formatting errors, then cast to pydantic when you're done for typehinting and validation in your IDE. If you're able to play around with it, let me know what you think.
Show HN: Promptfoo – CLI for testing & improving LLM prompt quality
Show HN: Promptfoo – CLI for testing & improving LLM prompt quality
Show HN: USearch – Smaller and Faster Single-File Vector Search Engine
Last week was insane for vector search. Weaviate raised $50M, and Pinecone raised $100M... That's a lot and makes you believe that vector search is hard. But it's not.<p>I have spent the last couple of days implementing a single-file vector search engine from scratch, which is at least the tenth in the twenty years of my career. But this time, it's different. Instead of inventing a brand new algorithm and doing some crazy optimizations on the GPU, I:<p>1. took the standard HNSW algorithm,
2. fitted into 1000 lines of C++11 for portability,
3. added quantization and hardware-accelerated metrics,
4. wrapped for Python, JavaScript, Rust, and Java, and
5. open-sourced it!<p>It was fun, and to my surprise, it performed well, reaching 300K QPS on Amazon c7g instances. I never had to use third-party vector search products, but the first testers of USearch suggested 3x performance improvement over their existing solutions.<p>My colleagues and friends are also adding bindings for GoLang and the Wolfram language. We will soon add Windows support, a standalone server, and a distributed version based on UCall we shared a month ago. There are, of course, but you can already use it!<p>One of the apparent use cases is Semantic Search platforms. The example at the end of the GitHub page shows how to use USearch, UCall, and the UForm transformers together to build up a text-to-image semantic search platform in just 20 lines of Python.<p>Try it and join the development! We also have a lot of open positions, especially for those who want to work with us on next-get algorithms and AI infra rather than polishing and repackaging existing ideas :)
Show HN: USearch – Smaller and Faster Single-File Vector Search Engine
Last week was insane for vector search. Weaviate raised $50M, and Pinecone raised $100M... That's a lot and makes you believe that vector search is hard. But it's not.<p>I have spent the last couple of days implementing a single-file vector search engine from scratch, which is at least the tenth in the twenty years of my career. But this time, it's different. Instead of inventing a brand new algorithm and doing some crazy optimizations on the GPU, I:<p>1. took the standard HNSW algorithm,
2. fitted into 1000 lines of C++11 for portability,
3. added quantization and hardware-accelerated metrics,
4. wrapped for Python, JavaScript, Rust, and Java, and
5. open-sourced it!<p>It was fun, and to my surprise, it performed well, reaching 300K QPS on Amazon c7g instances. I never had to use third-party vector search products, but the first testers of USearch suggested 3x performance improvement over their existing solutions.<p>My colleagues and friends are also adding bindings for GoLang and the Wolfram language. We will soon add Windows support, a standalone server, and a distributed version based on UCall we shared a month ago. There are, of course, but you can already use it!<p>One of the apparent use cases is Semantic Search platforms. The example at the end of the GitHub page shows how to use USearch, UCall, and the UForm transformers together to build up a text-to-image semantic search platform in just 20 lines of Python.<p>Try it and join the development! We also have a lot of open positions, especially for those who want to work with us on next-get algorithms and AI infra rather than polishing and repackaging existing ideas :)
Show HN: Niui 3.0 – lightweight, rich, accessible front end
Here is a library of the most common components I've created in the last decade. It aims to solve the toughest UI problems like Carousel, Modal and Select, while using native browser capabilities as much as possible, and focusing on accessibility, stability and customisation. 14 KB of CSS, JS optional.<p><a href="https://rado.bg/niui-3-0-native-internet-user-interface/" rel="nofollow">https://rado.bg/niui-3-0-native-internet-user-interface/</a>
Show HN: Niui 3.0 – lightweight, rich, accessible front end
Here is a library of the most common components I've created in the last decade. It aims to solve the toughest UI problems like Carousel, Modal and Select, while using native browser capabilities as much as possible, and focusing on accessibility, stability and customisation. 14 KB of CSS, JS optional.<p><a href="https://rado.bg/niui-3-0-native-internet-user-interface/" rel="nofollow">https://rado.bg/niui-3-0-native-internet-user-interface/</a>
Show HN: Niui 3.0 – lightweight, rich, accessible front end
Here is a library of the most common components I've created in the last decade. It aims to solve the toughest UI problems like Carousel, Modal and Select, while using native browser capabilities as much as possible, and focusing on accessibility, stability and customisation. 14 KB of CSS, JS optional.<p><a href="https://rado.bg/niui-3-0-native-internet-user-interface/" rel="nofollow">https://rado.bg/niui-3-0-native-internet-user-interface/</a>
Show HN: Stop nail-biting with your MacBook's webcam
Hey HN! I made this app because I bite my nails way too much while I code<p>It uses Mac's Vision library to track the location of your hands and mouth via the webcam.<p>Then when it catches you biting, it temporarily covers your screen with a big obnoxious warning. You have to stop biting if you want to continue seeing anything.<p>It's helped me a lot, so I hope it can help other nail-biters here :)
Show HN: Stop nail-biting with your MacBook's webcam
Hey HN! I made this app because I bite my nails way too much while I code<p>It uses Mac's Vision library to track the location of your hands and mouth via the webcam.<p>Then when it catches you biting, it temporarily covers your screen with a big obnoxious warning. You have to stop biting if you want to continue seeing anything.<p>It's helped me a lot, so I hope it can help other nail-biters here :)
Show HN: GPT crushes my high score in 2048.io
Show HN: Currl – A free text-based social bookmarking website
Show HN: Currl – A free text-based social bookmarking website
Show HN: Currl – A free text-based social bookmarking website
Show HN: I've built a spectrogram analyzer web app
Show HN: I've built a spectrogram analyzer web app
Show HN: I've built a spectrogram analyzer web app