Claude's extended thinking

Overview

Discussing Claude's new thought process Announcements Claude's extended thinking Feb 24, 2025 Some things come to us nearly instantly: "what day is it today?" Others take much more mental stamina, like solving a cryptic crossword or debugging a complex piece of code. We can choose to apply more or less cognitive effort depending on the task at hand.

Key Takeaways

Now, Claude has that same flexibility.
With the new Claude 3.7 Sonnet , users can toggle "extended thinking mode" on or off, directing the model to think more deeply about trickier questions 1 .
But it also raises many important questions for those interested in how AI models work, how to evaluate them, and how to improve their safety.
Some of our researchers with math and physics backgrounds have noted how eerily similar Claude's thought process is to their own way of reasoning through difficult problems: exploring many different angles and branches of reasoning, and double- and triple-checking answers.
Another issue is what's known as "faithfulness"-we don't know for certain that what's in the thought process truly represents what's going on in the model's mind (for instance, English-language words, such as those displayed in the thought process, might simply not be able to describe why the model displays a particular behavior).
The problem of faithfulness-and how to ensure it-is one of our active areas of research.
These latter concerns will be particularly acute for future, more capable versions of Claude-versions that would pose more of a risk if misaligned.

Continue Learning

Foundations

AI Fundamentals: Your First Steps

Comments

Comments appear only after moderation. Your email identifies your submission to the moderator and is never displayed here.

No approved comments yet.

Originally published by Anthropic

Read the original