ARC-AGI-2: The Next Challenge for AI Reasoning
What is ARC-AGI? Imagine giving a computer a puzzle that any 8-year-old could solve, but watching it struggle despite having […]
Research
When AI’s interest conflicts with ours
When AI’s interest conflicts with ours Building on our previous discussions of robot constitutions and the International AI Safety Report,
Real-Time Climate Controversy Detection
We are excited to announce the publication of our new research paper written in the context of our Innosuisse project
Improving LLMs with Multi-Agent Verification
Large Language Models (LLMs) can be improved by using more time and compute before coming up with a better answer
Fine-tuning Large Language Models for Stock Return Prediction Using Newsflow
Return forecasting plays a crucial role in identifying stocks with profit potential, making it a valuable tool for constructing investment
The key to Intelligence: “Wait…”
s1: Simple test-time scaling What better test of the adage ‘Think twice before speaking’? By instructing LLMs to pause and
Reasoning with long Chain-of-Thoughts
We are still in many ways trying to understand the way our own brains work. With the advancement of AI,
LLMs for Time Series: an Application for Single Stocks and Statistical Arbitrage
The below research paper, published at the end of last year, challenges the belief that Large Language Models (LLMs) are
Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach
This study introduces an advanced approach to stock market prediction following earnings reports by leveraging Large Language Models (LLMs) fine-tuned
ESG2Risk: A Deep Learning Framework from ESG News to Stock Volatility Prediction
Incorporating environmental, social, and governance (ESG) considerations into systematic investments have drawn numerous attention recently. In this paper, we focus