HNHacker News
TopNewBestAskShowJobs

ban-lan-gen

6 karma · joined April 15, 2021

submissionscomments
ban-lan-gen··on China's DeepSeek claims theoretical cost-profit ratio of 545% per day
Lookup the meaning of theoretical
ban-lan-gen··on Why OpenAI Models Struggle with PDF Extraction(and Why Gemini Fairs Much Better)
Does this only apply to PDFs with many images? If it is mostly text and table, could it just extract plain text?
ban-lan-gen··on RustGPT: ChatGPT UI Built with Rust, Htmx, SQLite
When I browsed GitHub repos. I came across some repos that implied "Because my thing is written in Rust, it automatically comes with a good performance, good scalability, etc". Jumping into a new language because people said it has good performance without actually understanding suited applications and the reason it gives a good performance seems to be a hype to me. It can be just my own bias. Maybe people out there already have a very solid understanding of Rust.
ban-lan-gen··on RustGPT: ChatGPT UI Built with Rust, Htmx, SQLite
I don't understand all those rust hypes here. What indeed does rust bring to the table?
ban-lan-gen··on Exllamav2: Inference library for running LLMs locally on consumer-class GPUs
Something like that 4^30 >>> 8^13?
ban-lan-gen··on NVIDIA introduces TensorRT-LLM for accelerating LLM inference on H100/A100 GPUs
They just want to sell some expensive hardwares?
ban-lan-gen··on Are any words the same in all languages?
Haha?
ban-lan-gen··on EvaDB – SQL Queries Using Hugging Face, Open AI, Ultralytics, PyTorch
Minor thing: the link redirects to the org but not the actual repo.
ban-lan-gen··on Why walking helps us think
I finally have some evidence to stop my wife's complaints.
ban-lan-gen··on Show HN: Vanna AI – Open-sourced text-to-SQL in Python
Just curious what kinds of models are used in your project?

https://arxiv.org/abs/2306.08891 One paper seems to suggest trained specialized model can outperform LLM in some tasks.