intelligence (AI) design, AI capability control proposals, also referred to as AI confinement, aim to increase our ability to monitor and control the behavior...

subfield of AI safety, the study of how to build safe AI systems. Other subfields of AI safety include robustness, monitoring, and capability control. Research...

to align AI goal systems with human values, and capability control, which aims to reduce an AI system's capacity to harm humans or gain control. An example...

progress in AI capability is inevitable because of economic pressures. Such pressures can already be seen in the development of existing AI technologies...

an existential catastrophe, it is necessary to successfully solve the "AI control problem" for the first superintelligence. The solution might involve instilling...

@AnthropicAI (October 22, 2024). "Introducing an upgraded Claude 3.5 Sonnet, and a new model, Claude 3.5 Haiku. We're also introducing a new capability in beta:...

greater chance that human inability to control AI will cause an existential catastrophe. In 2023, hundreds of AI experts and other notable figures signed...

Artificial intelligence (AI) refers to the capability of computational systems to perform tasks typically associated with human intelligence, such as learning...

from artificial general intelligence. MIRI's work has focused on a friendly AI approach to system design and on predicting the rate of technology development...

on – AI existential risk. Effective altruists (particularly longtermists) argue that AI companies should be cautious and strive to develop safe AI systems...

subfield of AI safety, the study of how to build safe AI systems. Other subfields of AI safety include robustness, monitoring, and capability control. Research...

feature is the capability of an AI algorithm to learn based on past data, such as in computer accompaniment technology, wherein the AI is capable of listening...

against the hypothetical risk of an AI takeover, and have advocated for the use of AI capability control in addition to AI alignment methods. Other fields...

first DGX-1 supercomputer to OpenAI in August 2016 to help it train larger and more complex AI models with the capability of reducing processing time from...

The object-capability model is a computer security model. A capability describes a transferable right to perform one (or more) operations on a given object...

refines their decision-making capability over time. While Deep learning, as opposed to rule-based methods, supports Agentic AI through multi-layered neural...

ISBN 978-1482234435 AI: Unexplainable, Unpredictable, Uncontrollable. Chapman & Hall/CRC Press, 2024, ISBN 978-1032576268 AI capability control AI-complete Machine...

Artificial general intelligence (AGI)—sometimes called human‑level intelligence AI—is a type of artificial intelligence capable of performing the full spectrum...

former OpenAI researcher Paul Christiano, ARC focuses on recognizing and comprehending the potentially harmful capabilities of present-day AI models. ARC's...

Mistral AI SAS is a French artificial intelligence (AI) startup, headquartered in Paris. It specializes in open-weight large language models (LLMs). The...

general-purpose AI, transparency requirements are imposed, with reduced requirements for open source models, and additional evaluations for high-capability models...

numerous AI ethics guidelines have been published in order to maintain social control over the technology. Regulation is deemed necessary to both foster AI innovation...

entities (including Shield AI) on its export control list, barring the export of dual-use commodities to that business. Shield AI employs machine learning...

Incentivizing Reasoning Capability in LLMs via Reinforcement Learning, arXiv:2501.12948 Gibney, Elizabeth (23 January 2025). "China's cheap, open AI model DeepSeek...

AI systems, as well as "tracking highly capable AI systems and large pools of computational capability" and "robust public funding for technical AI safety...

against and showing the capability to defeat professional teams. By choosing a game as complex as Dota 2 to study machine learning, OpenAI thought they could...

as little as 15 seconds of audio to reproduce a voice—a capability later corroborated by OpenAI in 2024. The service went viral on social media platforms...

proposed various approaches to mitigate risks associated with ASI: Capability control – Limiting an ASI's ability to influence the world, such as through...

intelligence (AI) startup company founded in 2021. Anthropic has developed a family of large language models (LLMs) named Claude as a competitor to OpenAI's ChatGPT...

in-memory computing capability. As of 2024[update], a typical AI integrated circuit chip contains tens of billions of MOSFETs. AI accelerators are used...