Show HN: AskYC - Startup advice from GPT Q&A bot based on YCombinator's YouTube
4 by ferbncode | 0 comments on Hacker News.
Direct link to the AskYC: https://ift.tt/PeHzE6i AskYC is a GPT-based Q&A bot that's based on every video on YC's youtube channel.
Sunday, 5 March 2023
New Show Hacker News story: latest news
Show HN: Lander, a lunar lander style web game
24 by ehmorris | 9 comments on Hacker News.
I’ve been working on this game for the past few weeks. It’s written in plain JavaScript, mostly with canvas, with no dependencies. The code is here: https://ift.tt/12YhKts
24 by ehmorris | 9 comments on Hacker News.
I’ve been working on this game for the past few weeks. It’s written in plain JavaScript, mostly with canvas, with no dependencies. The code is here: https://ift.tt/12YhKts
New Show Hacker News story: latest news
Show HN: Path 2.0, a Skilltree for Structured Self-Improvement
2 by mordymoop | 0 comments on Hacker News.
(You will need to make a (free) account on the website to try out the skilltree.) The Guild of the ROSE is excited to announce the full launch of the Practitioner's Path 2.0, a new framework for structured self-improvement via a carefully-designed skilltree. Founded two years ago, the Guild's mission is to provide structure and community for people interested in self-improvement. The Path skilltree is organized into three branches: - Pragmatist (red): Take direct action, make money, and expand your social network. - Meditative (green): Make art, improve your mental and physical health, and live a good life. - Empiricist (blue): Learn new skills, teach others, run experiments, and think clearly. The user is free to pursue a specific specialization, or to spread their efforts over the three trees.
2 by mordymoop | 0 comments on Hacker News.
(You will need to make a (free) account on the website to try out the skilltree.) The Guild of the ROSE is excited to announce the full launch of the Practitioner's Path 2.0, a new framework for structured self-improvement via a carefully-designed skilltree. Founded two years ago, the Guild's mission is to provide structure and community for people interested in self-improvement. The Path skilltree is organized into three branches: - Pragmatist (red): Take direct action, make money, and expand your social network. - Meditative (green): Make art, improve your mental and physical health, and live a good life. - Empiricist (blue): Learn new skills, teach others, run experiments, and think clearly. The user is free to pursue a specific specialization, or to spread their efforts over the three trees.
New Show Hacker News story: latest news
Show HN: I made a chatbot that debugs your code better than ChatGPT
2 by jshobrook | 1 comments on Hacker News.
I built this using semantic search and the ChatGPT API, which was just released the other day. What makes it special is it not only understands the code you're debugging, but also pulls in additional context like relevant documentation to help answer your questions and suggest code changes. Ultimately, my goal is to take the hassle out of pasting error messages into Google, finding a vaguely related StackOverflow post, and manually integrating the solution into your code.
2 by jshobrook | 1 comments on Hacker News.
I built this using semantic search and the ChatGPT API, which was just released the other day. What makes it special is it not only understands the code you're debugging, but also pulls in additional context like relevant documentation to help answer your questions and suggest code changes. Ultimately, my goal is to take the hassle out of pasting error messages into Google, finding a vaguely related StackOverflow post, and manually integrating the solution into your code.
New Show Hacker News story: latest news
Show HN: GraphQL-like full stack typesafe development for REST
2 by anttiviljami | 0 comments on Hacker News.
2 by anttiviljami | 0 comments on Hacker News.
Saturday, 4 March 2023
New Show Hacker News story: latest news
Show HN: GPT-grap. A simple, GPT-3 text to entity-relation graph generator
2 by mrsernine | 0 comments on Hacker News.
Hi HN! This is a simple text to entity-relation graph generator, powered by gpt-3 davinci model. The purpose is to feed it actual written data, to obtain a graph representation of entities and relationships mentioned in the text. Also, being able to identify entity attributes like gender, size, age ... My initial goal, was to make it able to process a large amount of text into a big single graph. The problem being the 4000 token limit the model has, I decided to take the approach of feeding the text in batches, and try to merge the incoming graph with the existing information each time. This is done by comparing the incoming node labels with those already in the graph, adding the new information to the existing nodes. This works somewhat, but sometimes entities get duplicated if they are mentioned slightly differently in the text. The comparation method could use some improvement clearly. A nice feature, is that you get to decide what types you want to extract. So if, for example, you are interested only in people, and companies in the text, you can tell the model to stick to that. You can also leave the types to the model discretion. Also, the application allows for saving / loading graphs to json files. These files can be used with Cytoscape Desktop Application, which is a nice side effect of using cytoscape.js. in the UI. I think tools like this can really be of help when going through dense documentation. To have a visual representation of the concepts, entities or whatever, can be really helpful in education, investigation, legal ... Would love to hear your thoughts on how this could be improved.
2 by mrsernine | 0 comments on Hacker News.
Hi HN! This is a simple text to entity-relation graph generator, powered by gpt-3 davinci model. The purpose is to feed it actual written data, to obtain a graph representation of entities and relationships mentioned in the text. Also, being able to identify entity attributes like gender, size, age ... My initial goal, was to make it able to process a large amount of text into a big single graph. The problem being the 4000 token limit the model has, I decided to take the approach of feeding the text in batches, and try to merge the incoming graph with the existing information each time. This is done by comparing the incoming node labels with those already in the graph, adding the new information to the existing nodes. This works somewhat, but sometimes entities get duplicated if they are mentioned slightly differently in the text. The comparation method could use some improvement clearly. A nice feature, is that you get to decide what types you want to extract. So if, for example, you are interested only in people, and companies in the text, you can tell the model to stick to that. You can also leave the types to the model discretion. Also, the application allows for saving / loading graphs to json files. These files can be used with Cytoscape Desktop Application, which is a nice side effect of using cytoscape.js. in the UI. I think tools like this can really be of help when going through dense documentation. To have a visual representation of the concepts, entities or whatever, can be really helpful in education, investigation, legal ... Would love to hear your thoughts on how this could be improved.
Subscribe to:
Posts (Atom)