DALL-E/Every illustration.

OpenAI’s New Model, Strawberry, Explained

ChatGPT’s next big evolution lies in its ability to solve the ‘strawberry’ problem

121 1

Was this newsletter forwarded to you? Sign up to get it in your inbox.


OpenAI has created a new model that could represent a major leap forward in its ability to reason. It’s called Strawberry. Here’s why:

If you ask ChatGPT how many “r”s are in the word “strawberry,” it famously fails miserably:

This occurs for two reasons. The first is that ChatGPT doesn’t actually see the word “strawberry.” Instead, it translates “strawberry” into an AI-readable language that represents words, not with letters, but with long strings of numbers. There’s no way for ChatGPT to count the number of letters in “strawberry.” It doesn’t see letters because of the way it’s built.

The AI researcher Andrej Karpathy likens what ChatGPT sees to hieroglyphs, rather than letters. So asking it to count the number of “r”’s in strawberry is a little like asking it to count the number of “r”’s in 🍓. The question doesn’t really make sense, so it has to guess.

The second reason is that, even though ChatGPT can score a 700 on an SAT math test, it can’t actually count. It doesn’t reason logically. It simply makes good guesses about what comes next based on what its training data tells it is most statistically likely. 

There are probably not many English sentences on the internet asking and answering how many “r”s are in the word strawberry—so its hunch is usually close, but not exactly right. This is true of all other math problems that ChatGPT is asked to solve, and it’s one reason why it often hallucinates on these types of inputs.

As initially reported by The Information, we don’t know a ton about Strawberry’s underlying architecture, but it appears to be a language model with significantly better reasoning abilities than current frontier models. This makes it better at solving problems that it hasn’t seen before, and less likely to hallucinate and make weird reasoning mistakes. Here’s what we know, and why it matters.

What Strawberry is

Strawberry is a language model trained through “process supervision.”

Process supervision means that during training, a model is rewarded for correctly moving through each reasoning step that will lead it to the answer. By comparison, most of today’s language models are trained via “outcome supervision.” They’re only rewarded if they get the answer right.

According to The Information, Strawberry “can solve math problems it hasn't seen before.” It can also “solve New York Times Connections, a complex word puzzle.” (I tried ChatGPT and Claude on Connections while writing this article. With the right prompting, I think I could get it to be a decent player, but it’s definitely not going to be expert-level.)

Subscribe to read the full article

Ideas and Apps to
Thrive in the AI Age

The essential toolkit for those shaping the future

"This might be the best value you
can get from an AI subscription."

- Jay S.

Mail Every Content
AI&I Podcast AI&I Podcast
Cora Cora
Sparkle Sparkle
Spiral Spiral

Join 100,000+ leaders, builders, and innovators

Community members

Already have an account? Sign in

What is included in a subscription?

Daily insights from AI pioneers + early access to powerful AI tools

Pencil Front-row access to the future of AI
Check In-depth reviews of new models on release day
Check Playbooks and guides for putting AI to work
Check Prompts and use cases for builders

Comments

You need to login before you can comment.
Don't have an account? Sign up!
Georgia Patrick 10 months ago

Dan.... you are our canary in the mine!!!! Your extreme curiosity, extraordinary talent, and high sensitivity with all 5 senses makes you the best person to poke the Strawberry around your work table when you get it. The best part, Dan? The best is your strength in writing clearly about the uniqueness; specifically, "Here's what's so great about this AI thingie" and "Here's where humanity still rules and is absolutely necessary for technology businesses to even exist."