iiinova — where your digital self keeps evolving

Chip Huyen @chiphuyen.bsky.social · 16/01/2025

Common pitfalls (with examples) when building AI applications, both from public case studies and my personal experience. huyenchip.com/2025/01/16/a... Would love to hear from your experience about the pitfalls you've seen!

huyenchip.com

Common pitfalls when building generative AI applications

As we’re still in the early days of building applications with foundation models, it’s normal to make mistakes. This is a quick note with examples of some of the most common pitfalls that I’ve seen, b...

06210

Chip Huyen @chiphuyen.bsky.social · 14/01/2025

I'm using AI so much for work that I can tell how productive I am by how many conversations I've had with AI. Script to generate this heatmap: github.com/chiphuyen/ai...

2571

Chip Huyen @chiphuyen.bsky.social · 09/01/2025

Finally got my copy! “AI Engineering” is officially out 🙏 🎉 It’s heavier than I expected (500 pages) and I’m so glad O’Reilly decided to publish it in color. Thanks everyone for making this happen! Thank you for giving this book a chance!

1314411

Chip Huyen @chiphuyen.bsky.social · 07/01/2025

My 8000-word note on agents: huyenchip.com//2025/01/07/... 1. An AI-powered agent's capability is determined by its tools and its planning ability 2. How to select the best tools for your agent 3. How to augment a model’s planning capability 4. Agent’s failure modes Feedback is much appreciated!

huyenchip.com

Agents

Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines ...

315329

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

O'Reilly said the first physical copies would appear around Dec 22 but my copies arrive on Jan 7 :(

020

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

6. AI Incident Database For those interested in seeing how AI can go wrong, this contains over 3000 reports of AI harms: incidentdatabase.ai

incidentdatabase.ai

Welcome to the Artificial Intelligence Incident Database

The starting point for information about the AI Incident Database

091

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

5. Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models (Lu et al., 2023) A cool study on LLM planners, how they use tools, and their failure modes. An interesting finding is that different LLMs have different tool preferences: arxiv.org/abs/2304.09842

arxiv.org

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Large language models (LLMs) have achieved remarkable progress in solving various natural language processing tasks due to emergent reasoning abilities. However, LLMs have inherent limitations as they...

150

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

4. Efficiently Scaling Transformer Inference (Pope et al., 2022) An amazing paper about inference optimization for transformers. It provides a guideline to optimize for different aspects, e.g. lowest possible latency, highest possible throughput, or longest context length: arxiv.org/abs/2211.05102

arxiv.org

Efficiently Scaling Transformer Inference

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better ...

100

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

3. Llama 3 paper The section on post-training data is a gold mine! It details different techniques they used to generate 2.7M examples for instruction finetuning. It also covers synthetic data verification! arxiv.org/abs/2407.21783

arxiv.org

The Llama 3 Herd of Models

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support ...

100

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

2. OpenAI’s best practices for finetuning While this guide focuses on GPT-3, many techniques are applicable to finetuning in general. It explains how finetuning works, how to prepare training data, how to pick hyperparameters, and common finetuning mistakes: docs.google.com/document/d/1...

docs.google.com

[PUBLIC] Best practices for fine-tuning GPT-3 to classify text

This document is a draft of a guide that will be added to a future revision of the OpenAI documentation. If you have any feedback, feel free to let us know. One note: this doc shares metrics for text...

100

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

The highlights: 1. Anthropic’s Prompt Engineering Interactive Tutorial The Google Sheets-based interactive exercises make it easy to experiment with different prompts. docs.google.com/spreadsheets...

docs.google.com

Anthropic's Prompt Engineering Interactive Tutorial [PUBLIC ACCESS]

120

Chip Huyen @chiphuyen.bsky.social · 13/12/2024

When doing research for AI Engineering, I went through so many papers, case studies, blog posts, repos, tools, etc. This repo contains ~100 resources that really helped me understand various aspects of building with foundation models. github.com/chiphuyen/ai...

github.com

58710

Chip Huyen @chiphuyen.bsky.social · 06/12/2024

Where are the AI people? Who should I follow?

9350

Chip Huyen @chiphuyen.bsky.social · 06/12/2024

Hello, world. So I caved and got on Bsky :-) I finally finished my book, AI Engineering, and I'm excited to get back to building. So many fun applications to build! What are you excited about?

141454