Resources

Advanced Prompt Engineering Techniques: Tree-of-Thoughts Prompting

BIG-Bench: The Behemoth Benchmark for LLMs, Explained

AI and Neural Networks: What Founders Need to Know

Deepgram and Universal Speech Solutions (Unispeech) Join Forces: Unlocking the Future of Voice Technology

Chain-of-Thought Prompting: Helping LLMs Learn by Example

Amp Up Your Privacy Controls: New Redaction Features from Deepgram

LegalBench: The LLM Benchmark for Legal Reasoning

Mixture of Experts: How an Ensemble of AI Models Decide As One

Introducing Nova-2: The Fastest, Most Accurate Speech-to-Text API

The Best AI API Playgrounds You Shouldn’t Miss in 2024

How Computing Hardware Drives AI Progress

Code Llama: Meta’s Answer to Generative AI Code-Writing

How Do Language Models Handle Obscure Words?

From Hawking to Siri: The Evolution of Speech Synthesis

Stay Updated in 2023: Top Artificial Intelligence Newsletters on Substack You Shouldn’t Miss

HumanEval: Decoding the LLM Benchmark for Code Generation

Unveiling ICML 2023: The Truth Behind the World’s Latest AI Research

Understanding Automatic Speech Recognition (ASR) in the Future of Communication

API-Bank: Benchmarking Language Models’ Tool Use

What Happens When AI Eats Itself

Sentiment Analysis with Hugging Face and Deepgram

AI Breakdown or: I Read the Entire 78-page Llama-2 Paper So You Don’t Have To

Parsing Fact From Fiction: Benchmarking LLM Accuracy With TruthfulQA

MMLU: Better Benchmarking for LLM Language Understanding

How to Forget Jenny's Phone Number or: Model Pruning, Distillation, and Quantization, Part 1

HellaSwag: Understanding the LLM Benchmark for Commonsense Reasoning

Human vs. Machine: A Comparative Study on Creativity in the Age of AI

Reviving Lost Tongues: How AI Battles Language Extinction

From Klingon to Simlish: Deepgram's AI Language Detection Adventures

The ARC Benchmark: Evaluating LLMs' Reasoning Abilities