541
Learning Regular Languages with L* Algorithm
Research in Software Engineering from Rahul Gopinath
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 673 posts.
542
LLMs have reached a point of diminishing returns
Science, sociology, and the likely financial collapse of the Generative AI bubble
543
SEQUOIA: Exact Llama2-70B on an RTX4090 with half-second per-token latency
Serving Llama2-70B on an RTX4090 with Sequoia
544
An open source DuckDB text to SQL LLM
Our first Text2SQL model release! | Reading time: 5 min read
545
546
Pixtral 12B
Pixtral 12B is deprecated. Discover Mistral AI’s latest vision models and capabilities in our updated documentation.
547
Shape Rotation 101: An Intro to Einsum and Jax Transformers
Acknowledgements First, I would like to acknowledge my friends and kind internet strangers who helped me with this post. This post heavily adapts from ...
548
Effort – a possibly new algorithm for LLM Inference
A possibly new algorithm for LLM Inference. Adjust smoothly - and in real time - how many calculations you'd like to do during inference.
549
OpenAI and Anthropic Revenue Breakdown
Breaking down revenue growth, the consumer subscription businesses and the importance of partnerships to the API business
550
EURISKO Lives
Programming blog of Eugene
551
Three major LLM releases in 24 hours
I’m a bit behind on my weeknotes, so there’s a lot to cover here. But first... a review of the last 24 hours of Large Language Model news. All times …
552
LLM that can call multiple tool APIs with one request
Learn about Cohere models' ability to perform multi-step tasks, enhancing productivity and efficiency.
553
Why Vivaldi won't follow the current AI trend?
Web browsers are integrating the current AI trend with Large Language Model (LLM) functionality. But there are fundamental issues with it. We address them.
554
555
Building an email-to-calendar LLM
Talk is cheap, show me the code Introduction A common problem my friends and I have is receiving actionable emails whose priorities are medium level. They do require action of some sort ($ \geq lowest\ priority$), but the action is due in the near future ($\leq highest\ priority$). I tend to skim over these emails…
556
Qwen2-Math
GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 This model mainly supports English. We will release bilingual (English and Chinese) math models soon. Introduction Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus…
557
Ten Noteworthy AI Research Papers of 2023
This year has felt distinctly different. I've been working in, on, and with machine learning and AI for over a decade, yet I can't recall a time when these fields were as popular and rapidly evolving as they have been this year. To conclude an eventful 2023 in machine learning and AI research, I'm excited to share 10…
558
Arc Prize 2024 Winners and Technical Report
Official winners and technical report.
559
Pgvector Is Now Faster Than Pinecone at 75% Less Cost
Meet pgvectorscale, an open-source PostgreSQL extension that supercharges pgvector’s vector search performance for large-scale vector workloads.
560
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
We introduce a depth completion network that allows generating geometrically coherent 3D scenes, and present a new benchmarking scheme for scene generation methods that is based on ground truth geometry.
561
Meta.ai Oh My
“Meet Your New Assistant” says the announcement , going on with “Built With Llama 3”. And oh my goodness has it ever got a lot of coverage. So I thought I might as well try it.
562
LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023
We analyzed topics covered by 100k Hacker News posts and the sentiments they evoke using Metaflow.
563
Diffusion models are evolutionary algorithms
Authors: Yanbo Zhang, Benedikt Hartl, Hananel Hazan, Michael Levin
564
Model Predictive Control in the Browser with WebAssembly
wrenfold is a framework for converting symbolic mathematical expressions (written in Python) into generated numerical code in other languages (C++, Rust, Python). It aims to bridge the gap between prototyping of functions in expressive symbolic form, and performant production code. wrenfold is particularly relevant to…
565
566
All You Need Is 4x 4090 GPUs to Train Your Own Model
How I built an ML rig for training LLMs locally, exploring hardware choices, setup tricks, and lessons learned along the way.
567
568
Mining JIT traces for missing optimizations with Z3
In my last post I've described how to use Z3 to find simple local peephole optimization patterns for the integer operations in PyPy's JIT. An example is int_and(x, 0) -> 0. In this post I want to scal
569
570
Implementing Neural Networks on a "10-cent" RISC-V MCU
I have been meaning for a while to establish a setup to implement neural network based algorithms on smaller microcontrollers. After reviewing existing solutions, I felt there is no solution that I…