Old vs. New Growth Trees and the Wood Products they Make
Plus, more links to make you a little bit smarter today.
A Multimodal Foundation Agent for Financial Trading
“Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks such as quantitative trading and high-frequency trading with various assets. While advanced AI techniques like deep learning and reinforcement learning are extensively utilized in finance, their application in financial trading tasks often faces challenges due to inadequate handling of multimodal data and limited generalizability across various tasks. To address these challenges, we present FinAgent, a multimodal foundational agent with tool augmentation for financial trading.”
The One Billion Row Challenge in Go: from 1m45s to 3.4s in nine solutions
“I saw the One Billion Row Challenge a couple of weeks ago, and it thoroughly nerd-sniped me, so I went to Go solve it.”
Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models
“Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important than the others. On the other hand, to fine-tune LLMs for such a task, one would need expert-annotated samples of explanation for every stock movement in the training set, which is expensive and impractical to scale.
To tackle these issues, we propose our Summarize-Explain-Predict (SEP) framework, which utilizes a verbal self-reflective agent and Proximal Policy Optimization (PPO) that allow a LLM teach itself how to generate explainable stock predictions, in a fully autonomous manner.”
Antarctic English
“Antarctic English is a variety of the English language spoken by people living on the continent of Antarctica and within the subantarctic islands. Spoken primarily by scientists and workers in the Antarctic tourism industry, it consists of various unique words and is spoken with a unique accent.”
Old vs. New Growth Trees and the Wood Products they Make
“It’s true what they say, “they don’t make ‘em like they used to.” We know, because our company restores historic windows. Many of these windows are still working well after 100 years. Most brand-new windows will not be in service 100 years from now.
Why? Because wood windows made with “new wood” aren’t made like they used to be. Historic windows made with “old growth” wood, from trees 100 years ago, are the most durable windows there are.”