OpenAI NewsShield utilizes OpenAI to assist IT technicians in handing over legacy portal work, with its Forge intelligent agent navigating the system, allowing technicians to focus on issues requiring manual judgment.
AWS Machine Learning BlogGS Caltex enables process engineers to build and validate models without code through Amazon SageMaker Canvas, and then configure deployment and scheduled inference using Amazon SageMaker Pipelines. ML engineers can transfer SageMaker Canvas assets to Pipelines in just a few hours, with model version deployment and execution history managed by Pipelines, achieving batch processing of inference every 30 minutes and reducing inference costs.
AWS Machine Learning Blog3434OpenFold3-preview can be deployed on Amazon SageMaker JumpStart, an open-source biomolecular structure prediction model developed by the OpenFold Consortium and AlQuraishi Lab at Columbia University, supporting 3D structure prediction for proteins, DNA, RNA, small molecule ligands, and their complexes.
AWS Machine Learning Blog4545Amazon Bedrock AgentCore runtime V2 reduces session startup time to about 2 seconds by preparing the environment once and using a snapshot for recovery, while also reclaiming unused memory. V2 supports building hooks to load large files or CLI, suitable for scenarios requiring resource preparation in advance. Session startup time can be measured via CloudWatch metrics, prioritizing optimization of platform overhead or code execution time.
AWS Machine Learning BlogDevelopers using coding agents like Claude Code and OpenAI Codex CLI need to be billed per task rather than per single call, so model routing should be based on the cost per task. NVIDIA NeMo Switchyard is an open-source library that helps AI agents select models to process each request, supporting Stage and Random routing strategies.
Codex releases00GitHub Copilot released version 0.171.0-alpha.5, providing code review, vulnerability detection, and secret scanning features, supporting enterprise-level code security and AI features.
Google ResearchFeatured8888Google has opened the /teamwork multi-agent workflow in Antigravity to external researchers and developers, which can be used in conjunction with Gemini 4 Argon, Carbon, and Hydrogen; /boost and Deep Review are also available.
Why it matters: Google has disclosed /teamwork's specific results in multi-agent research and engineering tasks and made it available for external researchers to use.
Claude Code releases1212Claude Code v2.1.325 released, fixing a security issue in zstd compression response decoding, adding a prompt to rerun Jupyter notebook cells in VS Code integrated terminal, and improving error handling and permission management features.
LangChain Deep Agents releases1515The deepagents-code module of LangChain Deep Agents has been released as version 0.2.8, adding the ability to set `DEEPAGENTS_CODE=1` in a local shell environment and fixing issues with unencodable characters in redirected output.
LangChain Deep Agents releases1212langchain-modal 0.0.8 has been released, fixing the `ModalSandbox` file I/O issue and updated to use the `Sandbox.filesystem` API
AWS Machine Learning Blog3838Amazon Bedrock tracks every inference call to an IAM principal with built-in zero instrumentation cost attribution, passing identity information and organizational tags to AWS Cost and Usage Reports (CUR 2.0) and AWS Cost Explorer while keeping data within AWS security boundaries.
AWS Machine Learning BlogAssemblyAI builds an elastic architecture on AWS by hybridly using EC2 On-Demand and Spot instances, and leveraging Amazon ECS, SQS, and EventBridge, to increase GPU instance utilization by 3.5 times, achieve cost reduction within the European AWS region, and meet service level agreements (SLA). Its inference platform is deployed on three GPU instance families: g4dn, g5, and g6.
Anthropic Research3434Anthropic suggests forming an evaluation team that includes domain and technical experts to monitor and evaluate in a offline sandbox in real time, and to select causal or observational designs based on the type of problem, while ensuring that evaluation metrics (such as rejection rates) align with the evaluation objectives, for example, rejecting answers in suicide-related scenarios is not an ideal behavior.
AWS Machine Learning Blog4242Amazon SageMaker HyperPod now offers Data Capture functionality, recording real-time inference input and output to Amazon S3, divided into three independent tiers to minimize latency impact.
Hugging Face BlogConstruct a pick-and-place simulation using the UR17G arm, Robotiq 2F-140 gripper, and beverage can in Isaac Sim, requiring checks on joints, motion, and contact behavior. SimReady Central provides asset models and simulation settings, and uses GPT-6 Sol to generate task code.
Ai2 BlogSame story · 2 outlets4040XYBench released, including 8K+ problem tests to evaluate how AI assistants handle requests based on misunderstandings; Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro often focus on the original incorrect method rather than the user's actual goal in the test.
How the accounts differ:Ai2 Blog states the benchmark includes 8K+ problems, while Hugging Face Blog mentions 8150 problems.
Meta EngineeringMeta has natively ported the Android Virtual Device framework Cuttlefish to macOS, by supporting QEMU and vhost-user, solving the technical challenges of running virtual devices on Apple Silicon, improving development efficiency, and unifying testing environments. The new version supports macOS's display, signing, and build processes, and expands features such as Bluetooth, Wi-Fi, and 3D graphics, allowing Mac developers to use high-fidelity virtual devices the same as CI.
Codex releases00GitHub Copilot 0.171.0-alpha.4 is released, including security features such as code review, vulnerability detection, and secret scanning.
Hugging Face BlogSame story · 2 outlets4040Hugging Face releases XYBench benchmark, containing 8150 real-world problems, to evaluate AI assistants' ability to identify user misunderstandings and guide them to correct solutions. Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro tend to focus on user errors (Y) rather than actual goals (X), with only 35-41% of responses centered on the actual goals.
How the accounts differ:Ai2 Blog states the benchmark includes 8K+ problems, while Hugging Face Blog mentions 8150 problems.
LangChain BlogFeatured6060Why it matters: LangChain announced $300 million in Series C funding and outlined the product structure of LangSmith in three layers: runtime, improvement, and governance, which can be used to determine the positioning of its Agent platform.
Databricks Blog5858OpenAI and Databricks collaborate to enable businesses to use OpenAI models on governed data. ChatGPT integrates with enterprise definitions through the Databricks Genie plugin, allowing employees to make decisions quickly; Codex is managed via Unity Gateway for enterprise AI coding; GPT models combined with Databricks App transform business processes.
OpenAI NewsThe ChatGPT Wallet allows intelligent agents in ChatGPT Work, Codex, and dots to complete purchases through user authorization and existing card payments.
Databricks BlogDatabricks has released Genie Migrate, now supporting migration to Lakehouse from Microsoft SQL Server, Azure Synapse, Teradata, Oracle, Snowflake, Amazon Redshift, and Google BigQuery, automatically converting SQL code to ANSI SQL.
LangChain Deep Agents releases2020LangChain Deep Agents 0.7.38 was released to fix the issue where `ls`, `grep`, and `glob` would incorrectly return results when soft link resolution exceeds the approved search scope.
Hugging Face BlogFeatured6565llama.cpp and ggml release v1.0.0, binding destructive changes to the public C API to the major version number, and both will be released according to semantic versioning rules thereafter. The project has supported over 150 model architectures and mainstream speculative decoding methods, and provides pre-release binaries for Linux, macOS, Windows, Android, iOS, as well as distribution channels such as Docker, Homebrew, and conda-forge.
Why it matters: llama.cpp and ggml are released simultaneously with v1.0.0, and the major version number corresponds to destructive changes to the C API, allowing downstream dependents to plan their upgrade schedule accordingly.
Ant Group inclusionAI · Hugging Face new modelsinclusionAI has released the Duo 1.2 causal-base model, a full-duplex multimodal world model for real-time audio-video interaction, featuring improved generation quality, and model weights can be downloaded from Hugging Face.
Ant Group inclusionAI · Hugging Face new modelsinclusionAI releases Duo-1.0-distill, a full-duplex multimodal world model for real-time audio-video interaction, including Realization weights with four-step distillation, which needs to be used in conjunction with the causal-base suite.
Ant Group inclusionAI · Hugging Face new modelsinclusionAI releases Duo 1.0 causal-base model, a full-duplex multimodal world model for real-time audio-video interaction, including implementation weights and backbones, intent models and adapters, audio-video encoders, speech recognizers, and forced aligners. The model weights are based on MiniMax H3 initialization and are open-sourced.
Ant Group inclusionAI · Hugging Face new modelsinclusionAI releases the Duo 1.0 Realization weights for FP8-quantized four-step distillation, used for its causal base model, supporting full-duplex real-time audio-video interaction, and needs to be overlaid with the causal base model weights.
Codex releases3030Claude Code 0.169.0 released, terminal workspace supports multi-side chat bubbles, can be switched by keyboard or mouse, can restore locally saved side chats after restart; search old tasks by name, hint preview, or working directory through the proxy command center; full-screen transcript can fold completed activities, answers are visible and tool outputs can be searched; supports adding or editing custom model providers from the terminal, uses device code for SSH or SSH authentication without local browser.
Codex releases00GitHub Copilot 0.171.0-alpha.2 has been released, the AI coding agent is used for tasks, projects, and automation work, supporting code review, collaboration, and cloud-based development environments.
Codex releases00GitHub Copilot rust-v0.171.0-alpha.3 released, this version is used for code review and collaboration.
Ant Group inclusionAI · Hugging Face new modelsSingVL-4B GGUF is the GGUF version of the 4B parameter multimodal decision-making model Sing VL S1 based on Qwen3.5, which can answer named entity questions with text or JSON and up to four images, and uses a full forward pass scoring option, scoring 69.76 in the Text evaluation and 73.94 in the Vision evaluation. The model uses the llama.cpp adapter, with a default context size of 4096 tokens, supporting text and image input.
OpenAI NewsAmplitude's product intelligent agent Wave is mainly based on the OpenAI model and can proactively identify development directions, assist teams in quickly deploying changes through coding intelligent agents, and evaluate the impact results.
Codex releases00GitHub Copilot has released version 0.171.0-alpha.1, offering code generation, review, and security detection features, supporting enterprise integration and support services.
OpenAI NewsGondola helps creative professionals gain recognition and job opportunities, with Codex boosting the output of its chief engineer by 50% and ChatGPT simplifying daily work.
GitHub Blog · AI & ML5858Agent skills allow the capture of reusable instructions for users and agents, defining the timing and manner of task execution through a versioned directory centered around a SKILL.md file. Proof Agent uses an independent validator for adversarial validation of AI-generated content, while Data Forge constructs a support pipeline for table metrics through multiple collaborative skills, with each skill sharing context defined by a manifest rather than independently rediscovering it.
Databricks Blog2222Lakebase architecture serves both Postgres and analytics with a single persistent data copy, without the need for CDC pipelines or a second database. This architecture stores data hierarchically in object storage and cache, not traditional replication. It supports both point-in-time and scan access paths, optimized respectively using Postgres heap pages and Parquet format, with no additional synchronization tasks.
vLLM BlogDeepSeek-V4.1-Flash achieves a service capability of 1.7M tokens/s per GPU in a single NVIDIA Vera Rubin NVL72 rack, reaching up to 387 tokens/s per user, an increase of 58 times compared to GB300 NVL72.
