The Download: Claude’s inner workings and OpenAI’s “super app”
This newsletter covers recent advancements in AI, specifically Anthropic's research into the internal 'J-space' of the Claude model. It also touches on OpenAI's new 'super app' and other significant tech industry news.
Why it matters
Understanding the internal mechanisms of LLMs is critical for AI safety and transparency as these models become more integrated into daily work tools.
Plus: OpenAI has unveiled its long-awaited "super app."
This is today's edition of The Download , our weekday newsletter that provides a daily dose of what's going on in the world of technology.
The AI firm Anthropic has got the clearest glimpse yet at what’s really going on inside large language models as they answer questions or carry out tasks. What they found ranges from the mundane to the unnerving.
Researchers at the company built a tool called the Jacobian lens (or J-lens) and used it to uncover a hidden area, which they named the J-space, inside its flagship LLM, Claude.
The J-space contains words related to the response a model is working on but may not ultimately produce. If Claude were a person (which it is not), you might say these hidden words reveal what’s on its mind before it actually speaks.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in