The Batch

Letters from Andrew Ng

Personal messages to the AI community

Concrete Ideas Make Strong AI Startups: AI startups can move more efficiently and effectively with a concrete product idea than a vague market concept.
Letters

Concrete Ideas Make Strong AI Startups: AI startups can move more efficiently and effectively with a concrete product idea than a vague market concept.

AI’s usefulness in a wide variety of applications creates many opportunities for entrepreneurship.
A graphic of a hand placing a ballot into a box labeled "Vote."
Letters

Threats to Democracy and How AI Can Help: Democracy empowers each citizen to help decide who governs. AI can be a complementary force: Widespread access to technology empowers people to work toward positive goals.

“Democracy is the worst form of government, except for all the others,” said Winston Churchill.
California’s Proposed AI Safety Law Puts Developers at Risk: California SB 1047 is intended to make AI safer, but its unclear requirements put developers, innovation, and open source in jeopardy.
Letters

California’s Proposed AI Safety Law Puts Developers at Risk: California SB 1047 is intended to make AI safer, but its unclear requirements put developers, innovation, and open source in jeopardy.

I continue to be alarmed at the progress of proposed California regulation SB 1047 and the attack it represents on open source and more broadly on AI innovation.
The World Needs High-Quality AI Education More Than Ever: AI developers need high-quality education and training to keep up with changing technology and gain useful skills. At DeepLearning.AI, we put learners first.
Letters

The World Needs High-Quality AI Education More Than Ever: AI developers need high-quality education and training to keep up with changing technology and gain useful skills. At DeepLearning.AI, we put learners first.

As we reach the milestone of the 256th issue of The Batch, I’m reflecting on how AI has changed over the years and how society continues to change with it.
AI is a Tool, Not a Separate Species: Should AI developers be allowed to train models freely on the contents of the web? The lawsuit by Sony, Universal, and Warner against AI music generators Suno and Udio raises difficult questions.
Letters

AI is a Tool, Not a Separate Species: Should AI developers be allowed to train models freely on the contents of the web? The lawsuit by Sony, Universal, and Warner against AI music generators Suno and Udio raises difficult questions.

On Monday, a number of large music labels sued AI music makers Suno and Udio for copyright infringement. Their lawsuit echoes The New York Times’ lawsuit against OpenAI in December.
Coding Agents Are Evolving From Novelties to Widely Useful Tools: Three reseach papers offer outstanding ways to use large language models to build coding agents that perform software development tasks automatically.
Letters

Coding Agents Are Evolving From Novelties to Widely Useful Tools: Three reseach papers offer outstanding ways to use large language models to build coding agents that perform software development tasks automatically.

On Father’s Day last weekend, I sat with my daughter to help her practice solving arithmetic problems.
Welcoming Diverse Approaches Keeps Machine Learning Strong: What technology counts as an “agent”? Instead of arguing, let's consider a spectrum along which various technologies are “agentic.”
Letters

Welcoming Diverse Approaches Keeps Machine Learning Strong: What technology counts as an “agent”? Instead of arguing, let's consider a spectrum along which various technologies are “agentic.”

One reason for machine learning’s success is that our field welcomes a wide range of work.
Blenders Versus Bombs, or Why California’s Proposed AI Law is Bad for Everyone: California’s proposed AI law SB-1047 stifles innovation and open source in the name of safety.
Letters

Blenders Versus Bombs, or Why California’s Proposed AI Law is Bad for Everyone: California’s proposed AI law SB-1047 stifles innovation and open source in the name of safety.

The effort to protect innovation and open source continues. I believe we’re all better off if anyone can carry out basic AI research and share their innovations.
We Need Better Evals for LLM Applications: It’s hard to evaluate AI applications built on large language models. Better evals would accelerate progress.
Letters

We Need Better Evals for LLM Applications: It’s hard to evaluate AI applications built on large language models. Better evals would accelerate progress.

A barrier to faster progress in generative AI is evaluations (evals), particularly of custom AI applications that generate free-form text.
Project Idea — A Car for Dinosaurs: AI projects don’t need to have a meaningful deliverable. Lower the bar and do something creative.
Letters

Project Idea — A Car for Dinosaurs: AI projects don’t need to have a meaningful deliverable. Lower the bar and do something creative.

A good way to get started in AI is to start with coursework, which gives a systematic way to gain knowledge, and then to work on projects.
Beware Bad Arguments Against Open Source: Big companies are lobbying governments to limit open source AI. Their shifting arguments betray their self-serving motivations.
Letters

Beware Bad Arguments Against Open Source: Big companies are lobbying governments to limit open source AI. Their shifting arguments betray their self-serving motivations.

Inexpensive token generation and agentic workflows for large language models (LLMs) open up intriguing new possibilities for training LLMs on synthetic data...
Building Models That Learn From Themselves: AI developers are hungry for more high-quality training data. The combination of agentic workflows and inexpensive token generation could supply it.
Letters

Building Models That Learn From Themselves: AI developers are hungry for more high-quality training data. The combination of agentic workflows and inexpensive token generation could supply it.

Inexpensive token generation and agentic workflows for large language models (LLMs) open up intriguing new possibilities for training LLMs on synthetic data. Pretraining an LLM
Why We Need More Compute for Inference: Today, large language models produce output primarily for humans. But agentic workflows produce lots of output for the models themselves — and that will require much more compute for AI inference.
Letters

Why We Need More Compute for Inference: Today, large language models produce output primarily for humans. But agentic workflows produce lots of output for the models themselves — and that will require much more compute for AI inference.

Much has been said about many companies’ desire for more compute (as well as data) to train larger foundation models.
Proposed ChatDev architecture, illustrated.
Letters

Agentic Design Patterns Part 5, Multi-Agent Collaboration: Prompting an LLM to play different roles for different parts of a complex task summons a team of AI agents that can do the job more effectively.

Multi-agent collaboration is the last of the four key AI agentic design patterns that I’ve described in recent letters.
Agentic Design Patterns Part 4, Planning: Large language models can drive powerful agents to execute complex tasks if you ask them to plan the steps before they act.
Letters

Agentic Design Patterns Part 4, Planning: Large language models can drive powerful agents to execute complex tasks if you ask them to plan the steps before they act.

Planning is a key agentic AI design pattern in which we use a large language model (LLM) to autonomously decide on what sequence of steps to execute to accomplish a larger task.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox