Anthropic makes a breakthrough in opening AI’s ‘black box’

Quick Summary:

The new method allows researchers to learn more about how large language models like Claude 'think.

Instead, concepts that are common across languages are embedded in the same set of neurons within the model and the model seems to “reason” in this conceptual space and only then convert the output to the appropriate language.

Baston said that thanks to the kinds of techniques that he and other scientists are developing to probe these alien LLM brains—a field known as “mechanistic interpretability”—rapid progress is being made.“I think in another year or two, we're going to know more about how these models think than we do about how people think,” he said.“Because we can just do all the experiments we want.

---

More Pictures

---

Read Quick SummarySave Time

or

Article Details

Author / Journalist: Jeremy Kahn

Category: EconomyBusiness

Markets: United States

Topics: Machine Learning A.I.

Source Website Secure: Yes (HTTPS)

News Sentiment: Neutral

Fact Checked: Legitimate

Article Type: News Report

Published On: 2025-03-27 @ 17:00:00 (5 days ago)

News Timezone: GMT +8:00

News Source URL: fortune.com

Language: English

Article Length: 1413 words

Reading Time: 8 minutes read

Sentences: 5 lines

Sentence Length: 283 words per sentence (average)

Platforms: Desktop Web, Mobile Web, iOS App, Android App

Copyright Owner: © Fortune

News ID: 27372483

View Article Analysis

About Fortune

Main Topics: EconomyBusiness

Official Website: fortune.com

Update Frequency: 63 posts per day

Year Established: 1929

Headquarters: United States

News Last Updated: 8 hours ago

Coverage Areas: United States

Ownership: Independent Company

Publication Timezone: GMT +8:00

Content Availability: Worldwide

News Language: English

RSS Feed: Available (XML)

API Access: Available (JSON, REST)

Website Security: Secure (HTTPS)

Publisher ID: #95

Publisher Details

Frequently Asked Questions