2024-12-22 · magazine.sebastianraschka.com

LLM Research Papers: The 2024 List

A curated list of interesting LLM-related research papers from 2024, shared for those looking for something to read over the holidays.

★ 2024-12-22 · arstechnica.com

Why AI language models choke on too much text

Compute costs scale with the square of the input size. That’s not great.

This is probably why Google charges twice as much, per token, for Gemini 1.5 Pro once the context gets longer than 128,000 tokens. Generating token number 128,001 requires comparisons with all 128,000 previous tokens, making it significantly more expensive than producing the first or 10th or 100th…
In a series of papers, Princeton computer scientist Tri Dao and several collaborators have developed FlashAttention, which calculates attention in a way that minimizes the number of these slow memory operations.
2024-12-21 · sugarspunrun.com

Vanilla Wafers Recipe

These vanilla wafers go perfectly with banana pudding, can be made in less than 30 minutes, and don't require chilling! Recipe includes a how-to video!

2024-12-21 · 99percentinvisible.org

Ten Thousand Years - 99% Invisible

In 1990, the federal government invited a group of geologists, linguists, astrophysicists, architects, artists, and writers to the New Mexico desert, to visit the Waste Isolation Pilot Plant. They would be there on assignment. The Waste Isolation Pilot Plant (WIPP) is the…

2024-12-20 · youtube.com

How to Make Vospov Kofte (Red Lentil Kofte)

Test cook Dan Souza makes a foolproof Vospov Kofte (Red Lentil Kofte) with host Bridget Lancaster. Get our Vospov Kofte recipe: https://cooks.io/3y0zFZt Buy our winning chefs knife: https://cooks.io/3tQ9mDh Buy our winning large saucepan: https://cooks.io/2QQbsgK Buy our winning…

2024-12-20 · nplusonemag.com

Casual Viewing | Will Tavlin

A decade before Airbnb persuaded homeowners to transform their homes into hotels, Netflix convinced its users to turn theirs into mini Netflix warehouses. Customers who held onto their DVDs for longer meant fewer shipping costs for Netflix, and fewer DVDs for the company to…

2024-12-19 · chicagomag.com

A Knife Forged in Fire

The author wanted a Japanese-style kitchen blade made for him by hand. What he witnessed was a combination of artistry and atomic magic.

2024-12-17 · theparisreview.org

Six Handbags - The Paris Review

“I lean close to the bag and inhale. I remember that the leather is baby-cow skin. I smell the earth, animal mortality, and the moment of my financial trauma.”

2024-12-16 · marktechpost.com

Meta AI Proposes Large Concept Models (LCMs): A Semantic Leap Beyond Token-based Language Modeling

Large Language Models (LLMs) have achieved remarkable advancements in natural language processing (NLP), enabling applications in text generation, summarization, and question-answering. However, their reliance on token-level processing—predicting one word at a time—presents…

However, their reliance on token-level processing—predicting one word at a time—presents challenges
LCMs perform computations in a high-dimensional embedding space. This space represents abstract units of meaning, referred to as concepts, wh