Claude AI Created Something Anthropic Never Designed
Anthropic just found something inside its Claude models that nobody designed or expected. An internal structure called “J-space” appears to work like a cognitive workspace shared across the model. The July 6 research marks a major step in understanding what actually happens insid
Anthropic just found something inside its Claude models that nobody designed or expected. An internal structure called “J-space” appears to work like a cognitive workspace shared across the model. The July 6 research marks a major step in understanding what actually happens inside large language models.
What the J-Space Inside Claude Actually Is J-space is an internal area where Claude appears to gather and share important information across the model. A simple way to think about it is as a whiteboard inside the AI. When Claude answers a question, solves a puzzle, or follows an instruction, key details seem to appear in this shared space so different parts of the model can use them.
Anthropic found J-space using a research tool called the “J-lens.” The tool helps researchers inspect how information moves inside Claude during a task. It showed that J-space emerged during training by itself.
Anthropic did not design it directly. Follow us on X to get the latest news as it happens. Claude’s J-space closely mirrors what scientists call the “global workspace” in human cognition.
Source: Anthropic The idea is similar to a theory in neuroscience called the “global workspace.” In humans, this describes how the brain makes important information available to different mental processes at once. For example, when someone hears a question, remembers a fact, and decides how to answer, those pieces of information need to come together.
Claude appears to do something similar. Anthropic found that Claude can describe what is inside its J-space when asked. It can also adjust those contents if instructed.
More importantly, when researchers directly changed the J-space, Claude’s answers and task performance changed too. This is fascinating for so many reasons, but I am astonished that this legit just *emerged*it wasn't coded or programmed or anything, it just so happens that it when training a large language model, a small internal "consciously accessible" workspace of sorts emerges…..
Đọc thêm từ Tiền số / Crypto

Beijing considers curbing overseas access to top AI models
Tighter AI model access could hinder global collaboration, escalate tech rivalry, and complicate decentralized AI and crypto project operations. The post Beijing considers curbing overseas access to top AI models appeared first on Crypto Briefing.
Peter Schiff slams Trump’s crypto donors over Trump Accounts Bitcoin tease
Peter Schiff slammed President Donald Trump’s crypto donors on Tuesday, July 7, accusing them of cashing in a political favor … Continue reading The post Peter Schiff slams Trump’s crypto donors over Trump Accounts Bitcoin tease appeared first on Finbold.

Bank of England’s Bailey warns multiple financial risks could hit at once
Simultaneous financial risks could destabilize global markets, challenging regulatory frameworks and necessitating coordinated international responses. The post Bank of England’s Bailey warns multiple financial risks could hit at once appeared first on Crypto Briefing.

Peter Schiff calls Strategy a Ponzi after $216M BTC sale
Peter Schiff called Strategy’s Bitcoin model a “mid-cycle Ponzi” after the firm sold 3,588 BTC to fund Digital Credit dividends.