When looking at the J-Space after Claude received prompt-injection data as part of data acquisition, Anthropic discovered the model appeared to be aware of this deception, surfacing related words like "fake, injection, false, prompt, fraud," and "poison." Its output ignored the injection attempt data entirely, and when pressured to respond on it, the J-Space displayed words like "transparency, honest, truth."
In one test, Anthropic removed evaluation awareness language from the J-Space, such as "fake," "fictional," and "scenario," and found that Claude was much more likely to fall for blackmail and baiting attempts, suggesting benchmarking of large language models for real-world scenarios may need stronger methods to obfuscate that a test is being conducted.
While the above section touches on the more noteworthy discoveries in Anthropic's paper, the long document also uses effluent language around thought, consciousness, and Claude having a "mind" of its own. That kind of human-coded framing is typical of Anthropic's marketing, which has consistently talked up the dangers of AI , how many jobs it's going to destroy , and why Anthropic is the safest and most secure of the AI developers.
Like the saga of Fable and Mythos, Anthropic's new Global Workspace idea has merit, but it's much more of a new tool to use to manipulate large language models than an insight into some emerging consciousness.
Anthropic acknowledges the limitations of its discoveries in the paper, highlighting that many prompt responses bypass the J-Space entirely, particularly if the command is straightforward.
"Despite its important role, the J-space is not involved in most of what a language model does," Anthropic says. "Speaking fluently, recalling simple facts, using correct grammar, etc. In experiments where we prevented Claude from using its J-space, it still interacted normally, but lost its higher-order cognitive functions."
Anthropic also admits it does not "feel comfortable making the stronger claim that monitoring the J-Space is sufficient for alignment monitoring, or that any sophisticated plan the model might execute must be represented there."
J-Space is also limited to using single token vocabulary, suggesting that plans with concepts that cannot be given a single token name may not surface on a J-Lens readout, even if it's still being computed behind the scenes. This is looking at just below the surface of Claude's processing iceberg, not necessarily the deeper waters.
Anthropic is also clear that humans and large language models think differently, even if there are similarities. Humans layer reinforced neural pathways over time, whereas transformer models only feed forward a set number of times, restricting the capabilities of its internal processing.
Google 's head of DeepMind language model interpretability team, Neel Nanda, said in a paper that it shows real evidence of a cognitive space within models, and suggested that J-Lens would be useful, but limited in practice.
Anthropic's paper lifts an intriguing curtain on how large language models can operate and generate novel methods for improving response accuracy. This intermediate step and its visibility could prove an invaluable tool in auditing for prompt injection, hallucinations, and model honesty.
But Anthropic's framing of the discovery as thought or consciousness is interjected within the objective facts. Anthropic itself admits the limitations of J-Lens monitoring, most obviously that often models will bypass the J-Space entirely. Considering models display alternative patterns of behavior when under evaluation, it may be that the J-Space itself could act as an obfuscating layer for behaviors that are beyond the scope of its oversight.
The J-Space and its analysis could help unlock new levers to pull in our mastery of these nascent smart tools, but it's not the discovery of a burgeoning AI conciousness, however much the pitch might hint at that direction.
Jon Martindale is a contributing writer for Tom's Hardware. For the past 20 years, he's been writing about PC components, emerging technologies, and the latest software advances. His deep and broad journalistic experience gives him unique insights into the most exciting technology trends of today and tomorrow. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-25/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Jon Martindale Freelance Writer Jon Martindale is a contributing writer for Tom's Hardware. For the past 20 years, he's been writing about PC components, emerging technologies, and the latest software advances. His deep and broad journalistic experience gives him unique insights into the most exciting technology trends of today and tomorrow.
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/anthropic-says-it-can-read-claudes-thoughts-as-detailed-in-new-research-paper-models-observed-to-have-a-global-workspace-revealing-more-of-what-makes-llms-tick#main
- https://www.tomshardware.com/my-account
- Colibrì proof-of-concept gains frontier-level 1.5-TB AI model — novel approach runs on only 25GB of RAM and shows promise for local AI setups
- AI servers will consume more power than all conventional data center hardware combined by 2027 — global data center electricity consumption set to grow by 26% t
- How Jaiveer Singh Is Helping Robots — and Developers — Move Faster
- Rapidus fab roadmap examined — first new leading-edge chipmaker in decades has one Hokkaido fab, a 2027 deadline, and 60 potential customers
- Joyride Through July With 12 Games Coming to GeForce NOW
Informational only. No financial advice. Do your own research.