~lobsters | Bookmarks (89)

clear filters

ai ×

🦌 Gazelle v0.2

tincans.ai

ai audio
2
Natural Language Processing in Bash

massimo-nazaria.github.io

Let’s implement a Bash toolchain to generate random prose that resembles the text corpus by using...
Let’s implement a Bash toolchain to generate random prose that resembles the text corpus by using the n-gram language model! A Glimpse at the Toolchain Basically, NLP aims at teaching computers to understand and work with human language by using different techniques. In what follows, we’re going to have a glimpse at...

ai unix
1
Feeding GPT Arbitrary Web Data – 1A Insecure Network

1a-insec.net

ai satire
1
Monty Anderson

montyanderson.net

ai culture philosophy
1
Notes on how to use LLMs in your product.

lethain.com

Pretty much every company I know is looking for a way to benefit from Large Language...
Pretty much every company I know is looking for a way to benefit from Large Language Models. Even if their executives don’t see much applicability, their investors likely do, so they’re staring at the blank page nervously trying to come up with an idea. It’s straightforward to make an argument for LLMs improving int...

ai
1
GitHub - karpathy/llm.c: LLM training in simple, raw C/CUDA

github.com

ai
2
TSAC: Very Low Bitrate Audio Compression

bellard.org

ai
2
The Assist @ Things Of Interest

qntm.org

At work we recently started experimenting with generative AI for assistance with programming. We have a...
At work we recently started experimenting with generative AI for assistance with programming. We have a new Visual Studio Code plugin which we can ask questions in English, and it spits back code. It was a really interesting piece of, well, mandatory training. I've formed some opinions. The main thing I dislike abou...

ai
3
Photoshop for text

stephango.com

ai
2
MDN’s AI Help and lucid lies

seirdy.one

ai web
3
GitHub - Zipstack/unstract: No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

github.com

ai api show
1
The Sweet Spot - Maximizing Llama Energy Efficiency · Jacques Mattheij

jacquesmattheij.com

tldr: limit your GPUs to about 2/3rd of maximum power draw for the least Joules consumed...
tldr: limit your GPUs to about 2/3rd of maximum power draw for the least Joules consumed per token generated without speed penalty. – Why run an LLM yourself in the first place? The llama.cpp software suite is a very impressive piece of work. It is a key element in some of the stuff that I’m playing around with on m...

ai
1
LLaMA Now Goes Faster on CPUs

justine.lol

ai performance
2
GitHub - rajtilakjee/keepyourmouthshut: Acid Reflux for your Ears!

github.com

ai audio python
1
How Meilisearch Updates a Millions Vector Embeddings Database in Under a Minute

kerollmops.com

This is part 4 of a series of blog posts. You can find part 1, part...
This is part 4 of a series of blog posts. You can find part 1, part 2, and part 3 on the blog. This blog post considers that you’ve already read parts 1 and 2. In this blog post, we’ll talk about how we implemented incremental indexing in Arroy. By incremental, we mean that when inserting or deleting items in a tree...

ai rust
1
Semgrep: AutoFixes using LLMs · Choly's Blog

choly.ca

Sun, Mar 24, 2024 Semgrep is an incredible tool that allows you to search code by...
Sun, Mar 24, 2024 Semgrep is an incredible tool that allows you to search code by matching against the Abstract Syntax Tree (AST). For instance, if you want to find all method calls named get_foo, you can write a pattern like this: $A.get_foo(...) Test your own patterns using the playground: https://semgrep.dev/play...

ai go
1
Redesigning OLTP for a New Order of Magnitude

infoq.com

Greef: The world is becoming more transactional, from servers to serverless, and per second billing. You...
Greef: The world is becoming more transactional, from servers to serverless, and per second billing. You used to buy a server every three years or rent dedicated by the month, then an instance by the hour, and now every second there's a serverless transaction. In the same way from coal to clean energy, our energy so...

ai database design databases distributed ml & data engineering
1
Claude and ChatGPT for ad-hoc sidequests

simonwillison.net

22nd March 2024 Here is a short, illustrative example of one of the ways in which...
22nd March 2024 Here is a short, illustrative example of one of the ways in which I use Claude and ChatGPT on a daily basis. I recently learned that the Adirondack Park is the single largest park in the contiguous United States, taking up a fifth of the state of New York. Naturally, my first thought was that it woul...

ai
1
pgvector vs. pgvecto.rs in 2024: A Comprehensive Comparison for Vector

pgvecto.rs

pgvector and pgvecto.rs are both vector search extensions designed to enhance the capabilities of PostgreSQL. These...
pgvector and pgvecto.rs are both vector search extensions designed to enhance the capabilities of PostgreSQL. These extensions revolutionize the way vector search is performed within the database, providing scalable, low-latency, and hybrid-enabled solutions. In this blog post, we will illustrate the differences bet...

ai databases
1
Let's Build AI

letsbuild.ai

ai
1
Thoughts on cloud GPU providers? | Lobsters

lobste.rs

Looking to get advice and additional insights on hosting large language models. I have gathered some...
Looking to get advice and additional insights on hosting large language models. I have gathered some preliminary information about several options, including: Lambda Labs - Good for obtaining GPU virtual machines (VM) or purchasing bare metal, however it lacks certain features like automatic web endpoints setup. What are your thoughts on its reliability and suitability for production workloads? Vast AI - Similar to Lambda...

ai ask
1
LLM inference speed of light

zeux.io

ai performance
2
Cataloguing my vinyl collection with computer vision | James' Coffee Blog

jamesg.blog

Every so often, a daunting thought comes to mind: I really should make a list of...
Every so often, a daunting thought comes to mind: I really should make a list of all of my vinyl records. I have previously recorded my collection in text files, but I always ran into the problem of context shifting (and, unrelated: I lost the file). Handling vinyls then writing information about them in text files ...

ai
2
Go, Python, Rust, and production AI applications

ajmani.net

ai go python rust
3