CtrlK

Explore AI Wiki

AI Wiki site footer

Browse by topic

All topics Random article

Machine Learning
AI Companies
Large Language Models
Robotics
Open Source AI
AI Models
Deep Learning
Humanoid Robots
AI Hardware
Generative AI
AI Compute

A free, source-backed encyclopedia with 4,000+ articles about artificial intelligence.

Help keep AI knowledge accurate

Start contributing

Contribute

Updates
Requested articles
Missing pages
Corrections log

Standards & trust

About AI Wiki
How we verify
Sourcing standards
AI transparency
Neutral point of view
Editorial policy
Content license

Tools & data

Free AI tools
AI comparisons
API, MCP & open data
Site statistics
RSS feed

From the AI Wiki team

View companion projects

AIWiki.ai · Text is available under CC BY 4.0; reuse welcome.

Contact
Privacy
Terms

HomeUpdates

Updates

2,489 articles changed in the last 30 days; 52 are new in the last 7 days. Dates show when an article's text last changed, so link and formatting passes do not move it up the list. Page 27 of 50.

All updates New articles

RSS

Wednesday, September 30, 2026

Physis-Langv3Physis-Lang is a research framework from NVIDIA, the Massachusetts Institute of Technology and the University of Oxford that uses structured natural language as a representation of physical processes for video…
Project Glasswingv4Project Glasswing is a restricted-access cybersecurity program run by Anthropic that gives selected companies, open-source maintainers and government bodies early use of its most capable Claude models for…
Dyna-2.1v4Dyna-2.1 (styled DYNA 2.1 in the company's press release) is a robot system announced by Dyna Robotics on 29 September 2026.
Gemini 3.8 Flashv6Gemini 3.8 Flash is a multimodal model in Google's Gemini family. Google DeepMind released it on September 2, 2026 as a generally available model for software engineering, tool-using agents, and knowledge work.
Jack Clarkv12Jack Clark is a British technology writer turned artificial intelligence policy executive who co-founded Anthropic in 2021 and serves as the company's Head of Public Benefit
C2PA (Coalition for Content Provenance and Authenticity)v10The Coalition for Content Provenance and Authenticity (C2PA) is an open technical standards body that develops Content Credentials, a cryptographically signed metadata format for tracking the provenance and…
The Anthropic Institutev8The Anthropic Institute is a research organization within Anthropic dedicated to studying the societal challenges posed by increasingly powerful artificial intelligence systems.
OpenAI Frontierv9OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents at scale.
AutomationBenchv3AutomationBench is a benchmark for AI agents, built by the automation company Zapier, that tests whether a model can finish a multi-step business workflow across several simulated software applications.
Gemini 3.6 Flashv5Gemini 3.6 Flash is a proprietary, multimodal large language model released by Google on July 21, 2026. It belongs to the Gemini 3 series and uses the stable API identifier gemini-3.6-flash.
Gemini 3.7 Flashv6Gemini 3.7 Flash is a proprietary, multimodal large language model released by Google on August 13, 2026.
Microsoft Agent 365v3Microsoft Agent 365 is a Microsoft product for observing, governing and securing AI agents across an organization.
DeepSWEv3DeepSWE is a benchmark for AI coding agents made by Datacurve, a San Francisco data company.
Existential risk from AIv11Existential risk from artificial intelligence (also called AI x-risk) is the hypothesis that the development of sufficiently advanced artificial intelligence could cause human extinction, permanent…
Clément Delanguev10Clément Delangue is a French entrepreneur and the co-founder and CEO of Hugging Face, one of the most prominent open-source artificial intelligence platforms in the world.
What If Automating AI R&D Triggers an Intelligence Explosion?v3"What if automating AI R&D triggers an intelligence explosion?" is a 22-author working paper published on September 28
Best AI Voice Generators (Text-to-Speech)v6As of July 2026, there is no single best AI voice generator: the right text-to-speech (TTS) tool depends on the job.
NVIDIA NemoClawv13NVIDIA NemoClaw is a collection of open blueprints (reference architectures) for building custom autonomous AI agents that packages three moving parts, a model, an agent harness, and a secure runtime
Gemini 2.5 Flashv9Gemini 2.5 Flash is a fast, cost-optimized multimodal large language model developed by Google DeepMind and the mid-tier member of the Gemini 2.5 family.
Gemini 2.5 Prov11Gemini 2.5 Pro is the flagship reasoning large language model of Google's Gemini 2.5 family, developed by Google DeepMind and first released as an experimental preview on March 25, 2025
Disaggregated servingv9Disaggregated serving is an LLM inference architecture that physically separates the prefill phase and the decode phase of text generation onto different sets of GPU hardware.
OpenClaw Enterprisev3OpenClaw Enterprise (OCE) is an open-source control plane for deploying, governing and auditing persistent AI agents on an organization's own infrastructure.

Tuesday, September 29, 2026

Adaptive thinkingv8Adaptive thinking is an inference-time reasoning mode in the Anthropic Messages API in which a Claude model decides, on a per-request basis, whether to use extended thinking at all and how much of it to spend
Cursor Composer 2.5v6Cursor Composer 2.5 is a proprietary agentic coding model built by Anysphere, the company behind the Cursor code editor.
Reasoning modelsv10Reasoning models are large language models that are post-trained or configured to spend additional inference-time computation on intermediate steps before returning an answer.
OpenAI IPOv6The OpenAI IPO refers to a reported and prospective initial public offering by OpenAI, the company behind ChatGPT, rather than a completed stock market listing.
Anthropic Life Sciences Verification Programv4

Monday, September 28, 2026

NVIDIA NeMo Agent Toolkitv7The NVIDIA NeMo Agent Toolkit is an open-source, framework-agnostic library for connecting, profiling, evaluating, and optimizing teams of AI agents.
NVIDIA Omniversev16NVIDIA Omniverse is a scalable, multi-GPU real-time 3D graphics collaboration and simulation platform developed by NVIDIA for building and operating industrial digital twins and physical AI applications.
NVIDIA Agent Toolkitv4NVIDIA Agent Toolkit is NVIDIA's umbrella name for its collection of open models, agent blueprints, libraries, skills and runtimes for building and running AI agents
AI Agentsv25An AI agent is a software system that selects and performs actions in an environment in pursuit of an objective.
AI safetyv15AI safety is the research and practice of preventing or reducing unacceptable harm from artificial intelligence systems.

Sunday, September 27, 2026

AI for Sciencev12AI for science is the use of artificial intelligence, particularly deep learning and large language models, to accelerate scientific discovery across biology, chemistry, physics, materials science…
Cloud AI GPU Pricing Comparisonv8Cloud AI GPU pricing is difficult to compare from a headline hourly rate alone. Providers sell different GPU variants, node sizes, CPU and memory bundles, regions, network configurations, and purchase models.
CME Compute Futuresv7CME Compute Futures are a planned family of financially settled futures contracts tied to Silicon Data benchmarks for hourly rentals of Nvidia H100 and B200 graphics processors.
Nebiusv8Nebius is an AI cloud company incorporated in the Netherlands and listed on the Nasdaq stock exchange under the ticker symbol NBIS
Array-associated reverse transcriptase (ART)

Friday, September 25, 2026

Microsoft Copilotv12Microsoft Copilot is the umbrella brand that Microsoft uses for its generative AI assistants and agents across consumer, developer, and enterprise products, and since August 2026 it is also the name of a…
InclusionAIv9inclusionAI is an open-source artificial general intelligence (AGI) research initiative established by Ant Group, the financial-technology affiliate of the Alibaba ecosystem.
Meta Connect 2026v7Meta Connect 2026 was the annual augmented reality, virtual reality and AI conference of Meta Platforms, held on September 23 and 24, 2026, at the company's headquarters in Menlo Park, California, and streamed…
A Severe Misalignment of AI in Mathematicsv5A Severe Misalignment of AI in Mathematics is a declaration about artificial intelligence and mathematical research, published on September 11, 2026 at mathandai.org with 25 initial signatories

Wednesday, September 23, 2026

Liang Wenfengv13Liang Wenfeng (Chinese: 梁文锋; born 1985) is a Chinese entrepreneur and engineer who founded the AI company DeepSeek in 2023 and co-founded the quantitative hedge fund High-Flyer (Huanfang Quantitative) in 2015.
Xiaomi CyberDogv7The Xiaomi CyberDog (Chinese: 铁蛋, pinyin Tiědàn, literally "Iron Egg") is a family of low-cost, open-source, bio-inspired quadruped robots developed by Xiaomi's Robotics Lab in Beijing.
Jiang Daxinv7Jiang Daxin (Chinese: 姜大昕) is a Chinese computer scientist and technology entrepreneur who is the founder and chief executive officer of StepFun (Chinese: 阶跃星辰), a Shanghai-based artificial intelligence…
Yan Junjiev9Yan Junjie (闫俊杰, born 1989) is a Chinese artificial intelligence researcher and entrepreneur who is the founder, chairman, chief executive officer, and chief technology officer of MiniMax, the Shanghai-based…
Luo Fuliv4

Wednesday, September 16, 2026

Calibration (machine learning)v9Calibration in machine learning is the property that the probability scores produced by a probabilistic classifier match the empirical frequency of the predicted event: a model that assigns a confidence of 0.8…
Structured outputv12Structured output is a set of techniques and API features that constrain a large language model (LLM) to emit responses that exactly conform to a predefined format or schema, such as JSON, XML, or a custom…
Long-context language modelsv9Long-context language models are large language models engineered to accept and reason over inputs far larger than the few-thousand-token windows used by early transformer systems, with frontier models in 2026…
Song Hanv6Song Han is a computer scientist and an associate professor with tenure in the Department of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT)
SparDA

NewerPage 27 of 50Older

The Life Sciences Verification Program (LSVP) is a trusted-access program run by Anthropic that lets vetted life sciences organizations use its Claude models with biology safeguards that are more permissive…

CursorBenchv3CursorBench is an agentic coding benchmark built and run by Cursor, the AI code editor made by Anysphere.

Agentic AIv10Agentic AI is an umbrella term for artificial intelligence systems that pursue a user-specified objective through a sequence of decisions and actions.

Open Secure AI Alliancev5The Open Secure AI Alliance is an industry coalition announced on July 27, 2026 to develop and share open technologies, techniques, and tools for securing software and AI agents.

Array-associated reverse transcriptases (ART) are a family of reverse transcriptase (RT) systems in the genomes of jumbo bacteriophages, announced by Anthropic on September 23, 2026 as early results from one…

Ragasv2Ragas is an open-source Python framework for evaluating applications built with large language models. It provides evaluation metrics, test-data generation, and tools for comparing experiments.

Octo (Robot Policy)v3Octo is an open-source generalist robot policy for manipulation. It uses a transformer and a diffusion action decoder to turn camera observations and a task description into robot actions.

Approximate Nearest-Neighbor Searchv2Approximate nearest-neighbor search (ANN or ANNS) finds points close to a query while allowing some error relative to an exact nearest-neighbor result. It is a family of search methods, not a single algorithm.

Claude Code Hooksv1Claude Code hooks connect Claude Code session events to automation, such as checking proposed tool calls or formatting edits.

LLM Model Routingv2LLM model routing is the selection of a large language model to handle a request from a pool of candidate models.

OpenAI Navier-Stokes Proposed Solutionv5

OpenAI Navier-Stokes Proposed Solution is a proposed resolution of the Navier-Stokes existence and smoothness Millennium Prize Problem announced by OpenAI on September 8, 2026.

SEMICON Westv4SEMICON West is the annual North American exhibition and conference for the semiconductor and electronics manufacturing supply chain, organized by the industry association SEMI.

Ming-Image-0.1-Designv3Ming-Image-0.1-Design is a family of open-weight image models for graphic design released by inclusionAI, the open-source AI initiative founded by Ant Group, and announced under Ant Group's Ant Ling brand on…

Advisory Group on Mathematics and Artificial Intelligencev4The Advisory Group on Mathematics and Artificial Intelligence (AGMAI) is an independent group of nine research mathematicians, hosted at the Institute for Advanced Study (IAS) in Princeton, New Jersey, that…

Advanced Voice Modev8Advanced Voice Mode is a real-time, spoken conversation feature in ChatGPT, developed by OpenAI, that lets users talk with the assistant using natural speech and receive spoken replies.

Meta Private Processingv3Private Processing is Meta's confidential computing infrastructure for running AI workloads on user data in its data centers.

AI Glassesv5AI glasses are eyeglasses that carry a camera, microphones, open-ear speakers and an AI assistant, and in most cases no display at all.

Virtual Realityv8Virtual reality (VR) is a computer-generated three-dimensional environment that a user can perceive, navigate and interact with in a way that simulates physical presence.

NVIDIA Newtonv8Newton is an open-source, GPU-accelerated physics engine built for robotics simulation and robot learning, co-developed by NVIDIA, Google DeepMind, and Disney Research and stewarded by the Linux Foundation.

NVIDIA DGX Cloudv7NVIDIA DGX Cloud is a managed AI-supercomputing-as-a-service offering from Nvidia that rents enterprises access to multi-node clusters of NVIDIA DGX infrastructure plus the NVIDIA AI software stack over the…

Meta Horizon Studiov4Meta Horizon Studio is a browser-based game-creation environment from Meta that turns natural-language prompts into playable 2D and 3D games.

Luo Fuli (Chinese: 罗福莉; also written Fuli Luo) is a Chinese AI researcher who leads the MiMo large-model team at Xiaomi.

Best AI Coding Assistantsv8As of 23 September 2026, the two tools at the top of the official Terminal-Bench 4.0 leaderboard are OpenAI's Codex and Anthropic's Claude Code.

Xiaomi (robotics)v14Xiaomi Corporation is a Chinese technology company whose robotics effort began as an internal quadruped project in 2020 and became the Xiaomi Robotics Lab, announced by founder Lei Jun on August 10, 2021.

UWORLD U1 Litev5UWORLD U1 Lite is the entry-level model of the UWORLD U1 series, a line of hyper-realistic companion humanoid robots from UBTECH Robotics sold under its consumer sub-brand UWORLD.

UWORLD U1 Ultrav5The UWORLD U1 Ultra is the premium flagship trim of the UWORLD U1 line of ultra-bionic companion humanoid robots, made by UBTECH Robotics and sold under its consumer UWORLD brand.

Aditya Rameshv5Aditya Ramesh is an artificial intelligence researcher at OpenAI, where he serves as a vice president of research and is best known as the creator of DALL-E

OpenAI Roboticsv3OpenAI Robotics is the robotics research and hardware group at OpenAI. OpenAI has worked on robots in two separate periods.

RadixAttentionv6RadixAttention is a KV cache management technique introduced in SGLang that uses a radix tree data structure to automatically share and reuse cached key-value tensors across inference requests.

UWORLDv5UWORLD is a consumer robotics brand launched in 2026 by UBTECH Robotics, the Shenzhen-based maker of the industrial Walker humanoid line.

Light-O1v3Light-O1 is a whole-body foundation model for humanoid robots developed by Light Origins (Chinese: 亮源新创), an embodied AI company with teams in Beijing, Shenzhen and Singapore.

Spirit AIv11Spirit AI (officially Spirit AI (Hangzhou) Technology Co., Ltd.; Chinese: 千寻智能; Qianxun Intelligence) is a Chinese robotics company headquartered in Hangzhou, Zhejiang, China, specializing in embodied…

Tang Jiev10Tang Jie (Chinese: 唐杰; born 1977), also published as Jie Tang, is a Chinese computer scientist, a chair professor at Tsinghua University, and a co-founder and controlling shareholder of Zhipu AI (now branded…

Yang Zhilinv7Yang Zhilin (Chinese: 杨植麟; pinyin: Yáng Zhílín) is the co-founder and chief executive officer of Moonshot AI (月之暗面), the Beijing startup that develops the Kimi chatbot and the Kimi family of large language…

DeepSeek Elastic Compute (DSec)v3DeepSeek Elastic Compute (DSec) is the production sandbox platform that DeepSeek uses to run the isolated execution environments behind agentic reinforcement learning (RL) training and evaluation of its…

Autonomous vehiclev9An autonomous vehicle, also known as a self-driving car, driverless car, or robotic vehicle, is a vehicle that uses artificial intelligence, sensors, and software to navigate and operate without human input.

Raterv7A rater is a person (or, increasingly, a model) who assigns labels, scores, or judgments to data items so those items can be used to train, evaluate, or align a machine learning system.

Dactyl (OpenAI)v7Dactyl was a robotics research project at OpenAI that used deep reinforcement learning to control a five-fingered, human-like robot hand and manipulate physical objects with high dexterity.

Mathematical reasoning in AIv7Mathematical reasoning in AI is the ability of computer systems to solve mathematical problems: carrying out multi-step calculations, proving theorems, and answering competition or research questions that…

Zhijian Liuv3Zhijian Liu is a computer scientist who works on efficient machine learning. He is an assistant professor at the University of California, San Diego, where he directs Z Lab, and a co-founder of Inco AI

Refusal directionv7The refusal direction is a finding from mechanistic interpretability research that the refusal behavior of safety fine-tuned chat language models is mediated by a single

Heretic (software)v3Heretic is an open-source command-line program that removes refusal behavior from transformer-based language models without retraining them.

SparDA (Sparse Decoupled Attention) is an add-on architecture for long-context large language model inference proposed by researchers at NVIDIA in a paper posted to arXiv on 3 June 2026.

NOSA (Native and Offloadable Sparse Attention)v3NOSA (Native and Offloadable Sparse Attention) is a trainable sparse attention mechanism designed so that most of a language model's KV cache can live in CPU memory during decoding without the CPU-to-GPU…

KV cache offloadingv3KV cache offloading is the practice of moving part or all of a Transformer model's KV cache out of accelerator memory (GPU HBM) into a larger, slower tier such as CPU DRAM, local NVMe storage, or remote…

AI browser agentv13An AI browser agent is a class of AI agent that uses artificial intelligence to autonomously navigate, interpret, and interact with web browsers to complete tasks on behalf of a user.

KernelBenchv6KernelBench is an AI benchmark and open-source evaluation environment that measures how well large language models can write fast and correct GPU kernels.

Dream-RSIv3Dream-RSI (Recursive Self-Improvement through Evolving Worlds) is a framework for improving the exploration strategy of an AI discovery agent, described in a preprint posted to arXiv on 14 September 2026 by a…

KV Cachev14KV cache, short for key-value cache, is transient model state used during Transformer generation.

Robot foundation modelv10A robot foundation model is a large-scale machine learning model, typically based on the transformer architecture, that is pre-trained on broad, diverse datasets of robot interactions and then adapted to a…

Jeff Hawkev3Jeff Hawke (published as Jeffrey Hawke) is a New Zealand robotics and machine learning engineer who is the co-founder and chief technology officer of Odyssey

NVIDIA NIMv10NVIDIA NIM (NVIDIA Inference Microservices) is a set of containerized, prebuilt-and-optimized model-serving microservices from NVIDIA that package an AI model, an optimized inference engine, and an…

Oliver Cameronv2Oliver Cameron is a technology entrepreneur and the co-founder and chief executive of Odyssey, an AI lab that builds general-purpose world models.