Show HN: Cleodora – Predicting the Future with GraphQL https://ift.tt/DsKra43

Show HN: Cleodora – Predicting the Future with GraphQL Making, tracking and improving personal forecasts (e.g. the weather tomorrow or your salary in 2 years). https://ift.tt/2sTtnx0 March 4, 2023 at 07:08PM

Show HN: Convert Quizes from Blackboard to Anki https://ift.tt/76MijEy

Show HN: Convert Quizes from Blackboard to Anki https://ift.tt/z5RTf79 March 4, 2023 at 02:22AM

Show HN: Community Building as a Service” https://ift.tt/NGlw8dZ

Show HN: Community Building as a Service” 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. https://ift.tt/dYj8XD2 March 4, 2023 at 05:06AM

Show HN: Watch ChatGPT debate itself on a given topic https://ift.tt/NIwdRUy

Show HN: Watch ChatGPT debate itself on a given topic https://opinionate.io/ March 4, 2023 at 05:03AM

Show HN: A Free form solution for your website https://ift.tt/UINL7um

Show HN: A Free form solution for your website https://formhouse.pro/ March 4, 2023 at 01:11AM

Show HN: Zipslicer, a library for loading LLM checkpoints on consumer hardware https://ift.tt/kY0ezCW

Show HN: Zipslicer, a library for loading LLM checkpoints on consumer hardware 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/bpjayVL https://ift.tt/fym41Q6 March 4, 2023 at 12:59AM

Show HN: Zazzani AI - ChatGPT for hackers, artists and writers from a single UI https://ift.tt/lgKjdRm

Show HN: Zazzani AI - ChatGPT for hackers, artists and writers from a single UI ChatGPT for hackers, artists and writers from a single UI https://ift.tt/4Rsi3Eq March 3, 2023 at 05:23AM