Runway launched the research preview of GWM Worlds 2, turning high-fidelity video and audio generation into real-time interactive simulation. It introduces the WorldPrompt input format, which can fix environmental elements such as the first frame and generate timestamped events.
Simon Willison released commit-rewriter 0.2. The tool relates to git, but the original text does not explain its specific functionality or update details.
GitHub Security Lab released Fuzzing Taskflow, an autonomous fuzzing pipeline for C/C++ projects. Given a GitHub repository, it identifies entry points, analyses build systems, writes harnesses, runs AFL++, reads coverage reports and improves harnesses, then classifies every crash and generates vulnerability reports.
On Wednesday, Meta released Ray-Ban glasses without cameras, allowing interaction with its AI only through voice. It also introduced new Ray-Ban frames and a cheaper Meta glasses range.
Remedy Entertainment's CONTROL Resonant joined GeForce NOW on launch day. Ultimate members can stream at GeForce RTX 5080-class performance with NVIDIA DLSS 4, ray tracing, NVIDIA Reflex and up to 5K HDR, without a 100 GB local installation.
YouTube announced Custom Feeds at its annual Made on YouTube event, generating personalised content tabs from descriptions and saving multiple feeds. It will launch soon for US web, mobile and TV users. GIF comments and group chats in YouTube messaging are also coming this year, initially limited to the US, UK, Singapore, Brazil and some European countries.
Dutch retailer HEMA built internal AI assistant HAL with MCP and Amazon Bedrock AgentCore, consolidating knowledge scattered across portals and wikis and delivering it directly into everyday tools such as Kiro and Claude.
Google released gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, providing over 2,000 voices and custom voices created from 30-second audio samples.
Google DeepMind announced an update to Private AI Compute that brings persistent, cross-device AI memory to the cloud while maintaining device-level privacy standards. Data is sealed in encrypted storage, with decryption keys retained only on user devices. When a model needs access, an end-to-end encrypted channel connects to a cloud secure enclave, where data is temporarily decrypted in isolated memory, then re-encrypted immediately after new context is saved.
Ringg's multilingual AI agents built on GPT-5.6 resolve up to 65% of customer calls across voice, chat, WhatsApp and web channels, at 90% lower cost than GPT-4.1.
invideo uses GPT-6 Astra for more precise editing plans, tripling colour grading and correction efficiency and generating 50 custom effects in a day.
Harvey uses GPT-6 Astra to produce better-structured, more contextually grounded legal documents, allowing lawyers to focus on strategy.
ChatGPT Ads expanded to Southeast Asia and Taiwan, covering over 60 countries and territories and enabling eligible businesses to reach more users.
Airbnb is expanding use of GPT-6 Astra and OpenAI frontier models to help engineering teams investigate bugs, design systems and deliver faster.
OpenAI improved prompt caching for GPT-6, adding higher cache-hit rates, new diagnostics, explicit breakpoints and controls to reduce latency and costs.
Simon Willison released llm 0.36 on 22 September 2026. The original does not specify its changes.
Simon Willison released llm-anthropic 0.29, the Anthropic plugin in his LLM command-line tool ecosystem. The original article gives no specific update details.
Simon Willison released the LLM plugin llm-typesafe 0.1a0 to connect TypeSafe AI's new Jev model to the LLM tool.
NVIDIA released Isaac ROS 5.0 at ROSCon in Toronto, Canada. The collection of ROS-based GPU-accelerated packages adds agentic workflows and platform support to help developers build, customise and deploy robot applications faster.
Parallel's agents use GPT-6 Astra to research and synthesise labour-market data, halving time and cost compared with earlier models.
Hugging Face added GGUF support to transformers. Users can choose a quantised checkpoint from the Hub and pass gguf_file to from_pretrained for local generation without additional configuration.
Higgsfield AI used GPT-6 Astra to launch new video features in a day, helping small businesses create video adverts and bringing creative tools to market faster.
OpenAI Academy added learning pathways for employees, developers, managers, educators, students and others to develop and demonstrate practical AI skills.
Hugging Face released tokenizers v1, preserving token IDs, APIs, vocabularies and merge ranks from v0.23 while increasing speed by up to tens of times.
V7 reduced costs by 78% with GPT-5.6 Luna while improving accuracy. GPT-5.6 turns scattered company documents into agent-ready context for completing complex work with source links.
Simon Willison released llm-keys-ui 0.1 to configure API keys on remote machines. Running uvx --with llm-keys-ui llm keys-ui --all opens an interface to save keys over the local network or a Tailscale device IP, avoiding pasting secrets into ChatGPT or agent sessions.
Pawprint Studio's open-world creature-catching RPG Aniimo launches day one on GeForce NOW, enabling streaming on Steam Deck and newly supported Firefox without waiting for a 45 GB download.
Cooley built GO Public on ChatGPT Work, bringing intelligence into IPO workflows to help lawyers spot potential issues earlier and focus judgement where it matters most.
OpenAI released OpenAI for Law, providing frontier intelligence, firm-specific workflows, connected legal data and legal-grade controls for confidential client work. It includes Astra for Law.
NVIDIA submitted preview results for Vera Rubin NVL72 to MLPerf Inference v6.1 for the first time, achieving throughput up to 3.7 times that of GB300 NVL72 on Qwen3-VL and up to 2.5 times on DeepSeek-R1.
OpenAI introduced new AI advertising experiences, including Sponsored Agents and tools for marketers, integrated with HubSpot and Shopify.
OpenAI described how ChatGPT Work and Codex analytics help teams understand AI usage and spending, identify training needs and connect adoption to business outcomes.
Hex's data agent uses GPT-6 Astra to turn analytical answers into interactive visual reports that employees want to share.
TypeSafe released Jev, a non-autoregressive model trained with RLCD solely for decisions, classification, routing and scoring. Official claims put it at 20–200 times faster and 40–400 times cheaper than small frontier LLMs, with no output token charges.
Salesforce unveiled its first CRM reasoning model, Koa, at Dreamforce. Post-trained on NVIDIA Nemotron 3 Super, it uses a proprietary synthetic dataset derived from nearly three decades of enterprise CRM deployments across more than 14 industries, including manufacturing, financial services, healthcare and travel.
NVIDIA introduced DSX at AI Infra Summit to improve AI-factory token throughput within a fixed power budget. Lambda validated DSX MaxLPS on a five-rack, 19-node HGX B200 cluster, running 19 nodes within the same budget as 16 at full power. Cluster token throughput rose 24%, from around four million to five million tokens per second, with performance per watt up 23%.
NVIDIA announced several advances for Vera Rubin and the DSX platform at AI Infra Summit, focusing on energy-efficiency improvements in token throughput per megawatt.
Children's Hospital of Philadelphia (CHOP) uses MONAI, the open-source medical imaging framework co-founded by NVIDIA, to reduce paediatric heart modelling from four hours to seconds, already supporting complex ventricular septal defect surgical planning. CHOP is working with NVIDIA to integrate Newton, an open-source physics engine based on NVIDIA Warp, into SlicerHeart, reducing cardiac-device simulation from up to four hours to near real time.
Fyxer combines OpenAI models, fine-tuning and memory with real user feedback to organise each user's inbox and draft emails in their own voice.
Perplexity is using GPT-6 Astra to draft communications, modify software and monitor production systems, checking the model much less frequently than earlier models.