Posts

New Show Hacker News story: Show HN: GraphQL-like full stack typesafe development for REST

Show HN: GraphQL-like full stack typesafe development for REST 2 by anttiviljami | 0 comments on Hacker News.

New Show Hacker News story: Show HN: ChatGPT, No Login Needed, Made with Official OpenAI API

Show HN: ChatGPT, No Login Needed, Made with Official OpenAI API 2 by liuxiaopai | 1 comments on Hacker News.

New Show Hacker News story: Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model

Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model 4 by sillysaurusx | 0 comments on Hacker News.

New Show Hacker News story: Show HN: gpt-graph. A simple, GPT-3 text to entity-relation graph generator

Show HN: gpt-graph. 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 s...

New Show Hacker News story: Show HN: Tiny Metasearch Engine to Find Software Developers

Show HN: Tiny Metasearch Engine to Find Software Developers 2 by mgl | 0 comments on Hacker News.

New Show Hacker News story: Show HN: Dependency free, fail-safe, UTF-8 ready, HD44780 driver

Show HN: Dependency free, fail-safe, UTF-8 ready, HD44780 driver 3 by dsab | 0 comments on Hacker News.

New Show Hacker News story: Show HN: Procal: A simple Qt-based programming calculator

Show HN: Procal: A simple Qt-based programming calculator 3 by fellerts | 0 comments on Hacker News.

New Show Hacker News story: Show HN: Convert Quizes from Blackboard to Anki

Show HN: Convert Quizes from Blackboard to Anki 2 by velocitatem | 0 comments on Hacker News.

New Show Hacker News story: Show HN: Community Building as a Service”

Show HN: Community Building as a Service” 2 by nobutakahemmi | 0 comments on Hacker News. Launched this week. Our team are experts in building online and offline communities from scratch. We've been helping our friends build this for free in the past. What we offer is best practices and resources for onboarding new members, moderating, and and growing online communities on Slack or Discord. We would love to get honest feedback and criticisms.

New Show Hacker News story: Show HN: Watch ChatGPT debate itself on a given topic

Show HN: Watch ChatGPT debate itself on a given topic 2 by frogboy | 0 comments on Hacker News.

New Show Hacker News story: Show HN: A Free form solution for your website

Show HN: A Free form solution for your website 2 by vasanthv | 0 comments on Hacker News.

New Show Hacker News story: Show HN: Zipslicer, a library for loading LLM checkpoints on consumer hardware

Show HN: Zipslicer, a library for loading LLM checkpoints on consumer hardware 11 by kir-gadjello | 1 comments on Hacker News. This is a low-level opensource library I developed for my own use and decided to share, as it makes it possible to process large checkpoints of neural networks without renting high-RAM instances, on a regular PC. It replaces torch.load() with a custom function that produces a dictionary that materializes tensors on the fly. Compared to other solutions it doesn't require sharding or re-encoding checkpoints and uses them completely as-is. It is a foundation to make it possible to run inference and compress language models and other large models one layer at a time - in principle, even one tensor at a time. I describe the rationale and technical details of the library's design in the blogpost: https://ift.tt/iAdeRDu

New Show Hacker News story: Show HN: Launching Taskivities – Task/Activities team logs

Show HN: Launching Taskivities – Task/Activities team logs 2 by yusufnb | 0 comments on Hacker News. From start to launch in 2 weeks. Please try and send feedback.

New Show Hacker News story: Show HN: Zazzani AI - ChatGPT for hackers, artists and writers from a single UI

Show HN: Zazzani AI - ChatGPT for hackers, artists and writers from a single UI 2 by zzinedddine | 0 comments on Hacker News. ChatGPT for hackers, artists and writers from a single UI

New Show Hacker News story: Show HN: Meeting Location Calculator

Show HN: Meeting Location Calculator 4 by jonashendel | 0 comments on Hacker News. Just enter the locations people will be traveling from. MLC then calculates the location, where the combined aircraft emissions are minimised. Based on data from the European Emissions Agency.