Three months ago Dwarkesh, who has been posting incredible blogs and episodes about RL, posted a framing question for his video essay on RLVR which upset a lot of Computer Use folks: We are no strangers to learning in public and are no strangers to the stress of getting things wrong when you have a big platform.
Amazon Bedrock Knowledge Bases adds the AgenticRetrieveStream API, which breaks multi-part insurance claims questions into subqueries and retrieves evidence over multiple rounds until there is enough to generate a cited answer.
The official AWS blog demonstrates deploying a three-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances. The composition agent uses Claude Sonnet 4.6 to generate a music brief and runs ACE-Step on the instance's NVIDIA L4 to render audio. The delivery agent reads .wav files from the shared volume for measurement and DSP processing, while the compliance agent independently remeasures them and checks harmonic similarity against a music catalogue.
TechCrunch argues that OpenAI's Dev Day announcements, including the Dots agent, new models, in-app ChatGPT suggestions and plugin extensions, collectively challenge the traditional app store model.
Shopify announced that browser-based AI agents can now complete purchases on merchant sites, extending their capabilities from product searches and adding items to carts to checkout. Built on WebMCP and covering Shop Pay, agents can read and update checkout pages and submit transactions with buyer authorisation, without relying on screenshots or web scraping.
At Tuesday's Dev Day, OpenAI announced an expansion of ChatGPT plugins. Developers can build app-like experiences, with dedicated sidebar entries for plugins and support for interactive panels and file viewers.
OpenAI announced a range of ChatGPT updates at DevDay, including the open Plugin Extensions system, shared workspace Space, collaborative documents Pages and Slides, Slack and Microsoft Teams integrations, automated workflows and an enterprise marketplace.
AI start-up Wabi, which previously let users build apps with prompts, has pivoted to messaging with Wabi 2.0, positioned as a personal agent that does things for users and instantly builds the interfaces they need. Users can generate apps such as calorie trackers and weightlifting logs within conversations. Access is currently offered only through invitation codes distributed on X.
At DevDay 2026, OpenAI unveiled the always-on agent Dots, which can independently take on tasks such as fixing bugs reported in Slack or sending forgotten invoices. It also launched the cheaper GPT-6.1 Sol, while the flagship GPT-6.1 Astra was held back over safety issues.
Prompt engineering determines the quality of Amazon Quick's AI responses to natural language requests. The first instalment of an official two-part series covers principles shared across components and reusable frameworks. It introduces CRISPE, covering context and constraints, roles and responsibilities, intent and inputs, steps and scope, and emphasises specificity, business context and examples over abstract descriptions.
AWS explains prompt-writing patterns for Amazon Quick components. Quick Research requires clear goals, audience and time scope, along with breaking down subquestions and restricting data sources (Quick Index).
Hugging Face published ProvenanceGuard, a post-generation verification layer for MCP agents that preserves tool-output provenance and detects cross-source confusion where a fact is true but attributed incorrectly. Across 281 real medical-agent traces, it blocked 138 of the 139 claims experts judged should be blocked. Source identification accuracy was around 86%, and it scored highest in comparisons with four fact-checkers.
Manus released version 2.0, expanding its AI agents into a platform with video editing, multiplayer game hosting, and personal agents that run through a phone number and can be controlled remotely from a phone. In the test configuration, the new Cascade agent framework used 23.2% fewer tokens than the previous system and reduced operating costs by 32%.
Anthropic's Thariq Shihipar discussed Claude Code's next phase on the Latent Space podcast, including Ask User Question, artifacts, Claude Tag, Projects and Claude Mods for customising the harness.
An agent-driven synthetic monitoring solution built on Amazon Nova Act and Amazon Bedrock AgentCore replaces Selenium and Playwright DOM-selector scripts with natural language actions. A multimodal LLM reads UI screenshots to execute critical flows such as login, ordering and checkout.
Simon Willison used Opus 5.5 to build a tool analysing any Bluesky account for automated reply-bot signals. These include replying within seconds, never posting original content or image links and replying only to high-follower accounts, and using question marks in replies. Bluesky's free API makes such investigations more feasible than on Twitter.
A canvas in the GitHub Copilot app is a customisable two-way interface. Entering /create-canvas in an agent session and describing a workflow generates boards, release checklists or dashboards without coding. Canvases are saved as extensions, shareable with projects or reusable personally, with community templates available through Awesome Copilot.
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.
Enterprises can build multi-account AI agent architectures with Amazon Bedrock AgentCore Gateway and MCP, keeping each business unit's data in its own AWS account and releasing it only as needed during queries.
Aderant used Amazon Nova Lite through Amazon Bedrock to build an intelligent ticket analyser for its 38-person SierraOps team, automating ticket context gathering, classification and routing.
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.
Simon Willison released the LLM plugin llm-typesafe 0.1a0 to connect TypeSafe AI's new Jev model to the LLM tool.
Simon Willison rejected the view that MCP is now a bad idea, arguing it retains irreplaceable value beyond terminal agents such as Claude Code and Codex with unrestricted internet access. MCP makes it easier to limit external service access, keep agents from directly handling API keys, provide connection and authentication interfaces and maintain strong audit logs. Dismissing it because fully capable coding agents do not need it overlooks other use cases.
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.
Latent Space's AINews roundup said Jev's launch video reached 36 million views within two days, with at least six reproductions or similar approaches: ModernBERT-based Laya, diffusion-based DiffusionGemmaJev, Qwen3.5-9B LoRA-tuned Bespoke Nimble, SemIf, Jevlike and Kev-0.5B.
The latest GitHub Podcast examines five AI development memes. AI-generated code still needs reading and accountability, with review proportional to risk. Skills package team experience, while MCP standardises connections to tools and data; they can combine. RAG is not dead: it provides relevant information beyond training data and can coexist with agents, Skills and MCP in one workflow.
At ACL 2026, Google Research proposed ToolGrad, an answer-first, question-later approach that generates real tool-call chains before deriving user queries, replacing traditional DFS trial-and-error annotation.
The Hugging Face team rebuilt most AUTOMATIC1111 functionality as the Workflow1111 canvas using Gradio Workflow. Its 11 media pipelines and 73 nodes cover text-to-image, high-resolution fixes, image-to-image, prompt matrices, VLM reverse prompting, detection-generated inpainting masks, ControlNet-style annotators, background removal, PNG Info and image-to-video.
OpenAI released the Agents API, a managed service powered by the Codex harness for building and launching cloud agents. It supports orchestration, long-running sessions and tool calls.
Hugging Face released funes, an open-source persistent memory layer for Claude Code, Codex, pi, Hermes and other coding agents. It indexes existing local sessions and performs embedding and reranking locally by default.
The IBM Granite team released Granite 4.2, its first dense, decoder-only reasoning model family, in 3B, 8B and 30B sizes, all open-source under Apache 2.0.
Hugging Face introduced gr.Workflow in Gradio to describe multi-step AI pipelines as graphs of typed nodes. Gradio provides a draggable canvas where each node can run and every intermediate result is visible.
Mistral released Agentic Search, a retrieval layer that lets models find, examine and verify information in multi-step retrieval loops. It is provided through Mistral Search Toolkit and built into Libraries in Studio and Vibe.
Mistral Studio now provides central management of Prompts and Skills, with version histories, clear ownership and traceability. Immutable versions, rollback, tags and audit logs make AI behaviour governable and discoverable, while Observability traces production outputs to their versions. Skills can be invoked directly from Studio as MCP servers, ensuring production executes the same governed asset.
Google DeepMind integrated computer use as a built-in tool in Gemini 3.5 Flash. Previously, it was available only as the standalone Gemini 2.5 computer use model.
Mistral AI added new Connectors capabilities. Admin controls for workspace- or organisation-level access and individual tool toggles are generally available, as are API keys scoped to connectors.
Mistral upgraded Le Chat to Vibe, a unified AI agent covering work and coding, retaining all existing conversations, settings and subscription plans.
Mistral AI released the public preview of Search Toolkit, a composable framework for production search pipelines in AI applications. It unifies ingestion, retrieval and evaluation through shared interfaces, is open-source and deploys in cloud, local or edge environments.
Mistral released Connectors in Studio. Built-in connectors and custom MCP are available through API/SDK for all model and agent calls, currently in public preview.
Mistral AI released Workflows in public preview, positioning it as an enterprise AI orchestration layer with durable execution, observability and fault tolerance to take AI workflows from proof of concept to production.