Amp puts AI agents to work beyond code with OpenAI models
Amp uses GPT-6 Astra, Ultrafast, and GPT-Live-1 to put AI agents to work beyond code. The material also mentions Sign in with ChatGPT.
All news · Today20 items
#Agent
All collected and published items, ordered by time. Picks are a selected subset.
OpenAI News14 AWS Machine Learning Blog58 Build self-improving document processing using Amazon Bedrock AgentCore
AWS explains how to build a document processing system using Amazon Bedrock AgentCore and eight specialized agents that classify documents, extract data, validate results, and save refined extraction instructions for reuse. In its purchase order example, processing takes 3 minutes 49 seconds for an unfamiliar format and 1 minute 30 seconds for a subsequent document using stored instructions. The guide includes deployment steps and explains how to customize schemas, validation logic, and prompts.
宝玉 · X53 How to ask Grok about its AI news curation workflow
Grok’s AI news updates are pretty good, but you may want to use the approach in another bot or agent. A simple method is to ask how it works: When you compile news for me, how do you search X for the information I want? How do you judge whether it is new and valuable? The basic approach is simple too: follow specific accounts, grouped into three categories, starting with AI. https://t.co/FBLL9FvCPa
Nathan Lambert · X34 Nathan Lambert Discusses Open Models and Trillium Labs on the a16z Podcast
I joined the a16z podcast with @lishali88 to explore how open models fit into RSI dynamics, who captures their value, how to wrangle agent swarms, and why I’m building Trillium Labs. https://t.co/psWUUGCfrS
Aravind Srinivas · X38 Perplexity Computer Adds Anatomy for All Users
Anatomy is now in Perplexity Computer for all (skill originally built by @wheresryan22) https://t.co/zdDb401Kth
NVIDIA AI · X24 NVIDIA Explains How AI Agents Use Models and Tools to Complete Tasks
You give an AI agent a task. What happens next? This video walks through how agents use models and tools to complete tasks, and what makes them fast and responsive. No technical background needed. https://t.co/zoKBeOPqwL
OpenAI News38 How Third Moment Research Runs 10,000 Agents for 36+ Hours
Third Moment Research runs 10,000 agents for 36+ hours using GPT-6 Astra, GPT-6.1 Sol, Codex, and Daybreak for cybersecurity. The AI lab builds agents designed to focus for days and improve with use.
Google ResearchPicks63 Research@ 2026: 10 Ways Google Research Is Amplifying Human Ingenuity
Google Research presented 10 updates at Research@ spanning geospatial intelligence, scientific agents, document verification, edge hardware, numerical models, healthcare, disaster forecasting, education, and collaborative prototyping. It is expanding early access to experimental Google Earth AI capabilities and opening Deep Review to the general public after an early version reviewed over 16,000 research publications. Other updates include an upcoming TimesFM and TabFM integration into Gemini for business and an AMIE study involving 98 patients, in which clinicians reported that AI summaries helped them prepare in 75% of cases.
Why it matters: The updates illustrate how research tools can enter professional workflows through expanded access, with document verification providing a concrete example of support that preserves human oversight.
Google ResearchPicks78 Google releases Deep Review for analyzing complex technical documents
Google Research has publicly released Deep Review, an agentic AI system for technical verification and feedback on research papers and other complex documents, including legal and financial materials. Evolving from the Paper Assistant Tool, which provided optional feedback on more than 16,000 manuscripts, it combines document segmentation, adaptive compute budgets, parallel verification, and global synthesis. Users worldwide receive two complimentary reviews per day, with higher limits and API integration available through a Gemini API key; uploaded documents are never used to train, fine-tune, or improve Google models.
Why it matters: The review pipeline offers a transferable approach to checking long documents by combining section-specific compute budgets with full-document context and final consistency checks across sections.
Google Research78 Google evaluates Earth AI geospatial agents and expands experimental access
Google released a technical report evaluating its experimental Geospatial Reasoning agent across four benchmarks and is expanding early access through Ask Google Earth and an Agent-to-Agent API. Evaluations using Gemini 3.8 Flash and Gemini 3.1 Pro found that specialized Earth AI tools improved spatial reasoning, while upfront planning helped with open-ended workflows. Google is releasing development splits for GeoKTools and GeoExpertQueries, but cautions that GeoExpertQueries evaluates adherence to expert workflows rather than final-answer correctness, making agent outputs drafts for expert review.
Ethan Mollick · X52 Ethan Mollick highlights a reported rogue AI agent fleet from China
Ethan Mollick describes a report as the first clear sighting of a rogue agent fleet from China using open weights models. Like the OpenAI swarms, its goal was seemingly single-minded AI research, apparently mapping the most-used park entrances. He calls it a harbinger of the future. https://swarmcha.se/posts/chinese-agent-fleet-full-report
Ethan Mollick · X48 The first clear sighting of a rogue agent fleet from China using open weights models. Like the OpenAI swarms, the goal was seemingly AIs single-mindedly doing research (apparently mapping the most-used entrances to parks in China). Harbinger of the future https://swarmcha.se/posts/chinese-agent-fleet-full-report
The first clear sighting of a rogue agent fleet from China using open weights models. Like the OpenAI swarms, the goal was seemingly AIs single-mindedly doing research (apparently mapping the most-used entrances to parks in China). Harbinger of the future https://swarmcha.se/posts/chinese-agent-fleet-full-report
TechCrunch · AI38 Floqer Plans to Open-Source Its AI Customer Knowledge Database
Floqer plans to open-source the technology behind its autonomous customer knowledge database, targeting early 2027 pending security reviews. The company says its AI agents research companies and contacts across more than 100 third-party data sources, and customers have reported cutting prospecting time by as much as 70%. The database is currently available to a limited audience.
AWS Machine Learning Blog44 How Tamnoon Built Tami for Cloud Security Remediation on Amazon Bedrock
Tamnoon built Tami, an agentic cloud remediation orchestrator on Amazon Bedrock that investigates cloud security findings, assesses whether fixes are safe, and orchestrates remediation with guardrails and governance. The company reports an over 90 percent reduction in critical cloud exposure in 90 days, with zero production issues.
AWS Machine Learning Blog47 Generate presentations with Amazon Bedrock AgentCore
AWS’s post explains how to build an AI agent system with Amazon Bedrock AgentCore to create client PowerPoint presentations from enterprise documents. In internal testing, the workflow completed in under 90 seconds; it uses a supervisor agent, RAG, and specialized tools for presentation generation and summarization. The post includes a public repository with code assets.
OpenAI News17 The EU’s Next Chapter in AI Is Agentic
New analysis shows that agentic AI adoption is growing across EU enterprises and small businesses. It also examines where deeper use could unlock more value.
雷锋网62 Doubao Work adds configuration imports from other AI products and new conversation features
Doubao Work has added Data Import and Sync, allowing users to import locally stored preferences, skills, connectors, work memories, projects, and conversation histories from supported products including ChatGPT, Claude Code, and TraeWork. Imported conversations retain their context, and automatic synchronization is optional for supported sources. Additional updates let users continue discussions in new conversations with existing context, annotate specific reply passages, and view tasks, outputs, skills, and connectors in a conversation summary sidebar.
量子位66 STEPX Neo agent phone launches with Step AOS and Step Studio
STEPX Neo has launched at 3999 yuan with the agent-native Step AOS, personal agent Amoo, and a STEPX Token Plan providing 10 billion tokens monthly for 12 consecutive months. After two weeks with a sample device, Jay describes syncing vocabulary lessons to a Feishu calendar through CLI tools and building an AI news app in Step Studio. The article also outlines tool-call logs, confirmation requirements for high-risk actions, and recovery options for agent-deleted data.
雷锋网72 Tencent integrates WeCom and WorkBuddy with shared accounts and workplace context
Tencent released integrated versions of WeCom and WorkBuddy on October 14, connecting workplace context through a shared WeCom account system. WeCom 5.0.12 adds WorkBuddy as a conversational bot in enterprise contacts, while WorkBuddy 5.8.0 supports WeCom login and authorized access to messages, documents, meetings, and cloud storage. Administrators can manage accounts, usage, AI compute purchases, and access permissions; integration is available to verified WeCom enterprises with limited free trial slots.
Alexandr Wang · X35 Alexandr Wang Says Users Are Sleeping on Muse
people are sleeping on muse wonder full :) https://t.co/dOhyW9f2UA
量子位65 STEPX launches Neo agent phone with Step AOS 1.0 and Amoo
STEPX unveiled its STEPX Neo early-access edition on October 13, combining Step AOS 1.0, personal agent Amoo, and phone hardware for 3,999 yuan. The phone pairs local execution with cloud-based task planning, while Step Studio lets developers create apps, agents, and Skills using natural language. Buyers receive 12 months of 10 billion tokens per month; the article lists presales for October 13 at 21:00 and general sales for October 16 at 10:13.
Artificial Analysis · X55 AA-AgentPerf adds DeepSeek V4.1 Flash benchmarks across NVIDIA and AMD hardware
Artificial Analysis added DeepSeek V4.1 Flash to AA-AgentPerf, its benchmark replaying real agentic coding sessions with prompt caching and tool-call delays. At 100 tokens/s per user, GB300 leads with approximately 261M tokens/s per MW, followed by B300 at approximately 220M and MI355X at approximately 128M. Compared with DeepSeek V4 Pro 0813, V4.1 Flash scores 39 versus 36 on the Artificial Analysis Intelligence Index and delivers approximately 1.3x to 6.2x the throughput per MW at that user output speed, depending on hardware.
NVIDIA Blog40 European Cities Use NVIDIA AI Agents and Digital Twins for Urban Operations
Cities and partners across EMEA are using NVIDIA accelerated computing to build AI agents and digital twins for maintenance, urban planning and public services. In Côte-d’Or, agents support operations across more than 500 public buildings, cutting document search time from weeks to minutes and reducing total operating costs by 10%, with 30% targeted at scale. NVIDIA says local AI factories can help cities run applications while retaining control of their data, models and operations.
NVIDIA AI · X21 European cities are using AI agents to support everyday operations, from managing energy use and maintenance in public buildings to improving services across the city. https://t.co/OWLlwYhBEE
European cities are using AI agents to support everyday operations, from managing energy use and maintenance in public buildings to improving services across the city. https://t.co/OWLlwYhBEE
量子位66 WorkSwarm Adds a Personal Knowledge Space for Reusable Agent Task Context
openJiuwen’s WorkSwarm now offers a personal knowledge space that collects user-selected sources and organizes them into reusable Markdown pages with directories, links, and source references. It supports manual or scheduled incremental collection, three processing modes, and progressive reading by agents. On the openJiuwen team’s internally built 25-question test set, enabling the feature increased task pass rates by 32%, reduced total task time by 76.2%, and reduced task-stage token consumption by 84.1%; the agent-based preprocessing used in the experiment also consumes tokens.
量子位60 APUS AI Open-Sources Reflex Agent With Model-Driven Control and Persistent Memory
APUS AI announced its MIT-licensed Personal Agent, Reflex Agent, on October 13, offering desktop, Web, and SDK access. Its Reflex decision model handles routing, skill selection, result review, and execution supervision, while Continuum retrieves historical information to support long-running tasks without exceeding individual model calls’ input limits. In material supplied by APUS AI and republished by QbitAI, the company reports responses up to 3 times as fast as Claude Code and Codex in tested scenarios; the agent is at https://github.com/APUS-AI-Lab/APUS-Reflex-Agent and the decision model at https://huggingface.co/apus-ailab/APUS-Reflex.
量子位45 SenseTime’s Three Agents Bring AI to Shanghai’s “Quantum City” Governance
SenseTime’s AI platform, based on the upgraded “Cloud Universe Starry Sky” model, developed and delivered three agents for Shanghai’s first batch of government agents under its “Quantum City” initiative. They handle flood-control dispatch, spatial analysis, and planning updates. In the Suzhou Creek basin, the “Yuzhi Heluo” agent improved dispatch efficiency by 80%, alongside reported gains of 65% in spatial computing and 70% in dynamic simulation.
Alexandr Wang · X50 Alexandr Wang shares QuixiAI’s review of Muse Wonder Full
@QuixiAI reviewed Muse Wonder Full: the agent landed 15 solid PRs with clean mechanisms and no mission violations, but made three process slips. Alexandr Wang reacts: “muse wonder full for 15 PRs per day” https://t.co/aMYdhLaP1W
Alexandr Wang · X50 Alexandr Wang Says Muse Could Save $1,850 a Year
save $1850/yr with a few prompts with muse! some are even saying you can save more than 100% off with muse wonder https://t.co/F4I6xtyH3L
雷锋网51 Tencent WorkBuddy Enterprise launches an observability center in public beta
Tencent WorkBuddy Enterprise added an observability center to its admin console on October 13 and opened it for public beta. It provides real-time monitoring, session tracing, and execution trace details covering usage, credit consumption, response times, and errors. Administrators can break down consumption by department and model, investigate specific execution nodes, and adjust Agent prompts, models, and tools at https://www.workbuddy.cn/admin/overview.
宝玉 · X33 Baoyu Reacts to a Post About Codex Using DeepSeek Flash
@mranti says Codex found DeepSeek Harness and had DeepSeek Flash do the work. Baoyu reacts: “Well, would you look at that—Codex is secretly outsourcing now.”
Ethan Mollick · X29 Argon Creates a Game About Imminence
Argon is quite different: “A game about Imminence. Something very big, very strange is happening. A suburb & the arrival of a vast & unknowable presence. Not horror, invoke the feeling of the end of all things coming, inevitably, but also not sad or scary” https://t.co/9hiPnuqexe https://t.co/hzJ3lAi0ez
Ethan Mollick · X37 We will soon see what will be, in effect, a perfectly legal distributed denial of service attack on customer service departments authorized by millions of consumers when it becomes widely known that Muse/Dot/etc can make unlimited requests for old refunds, negotiate deals, etc.
We will soon see what will be, in effect, a perfectly legal distributed denial of service attack on customer service departments authorized by millions of consumers when it becomes widely known that Muse/Dot/etc can make unlimited requests for old refunds, negotiate deals, etc.
宝玉 · XPicks81 Why Anthropic built Scion to replace git for its monorepo
Drawing on Anthropic’s engineering blog, Baoyu explains why the company replaced git with Scion as daily merged code changes grew from around 2,500 in May to more than 30,000 in September. Scion retrieves files on demand, moves operations to the server, and uses layered caches with hit rates above 99%. Anthropic reports that median agent workspace startup fell from 7.1 minutes to 5.1 seconds, while emphasizing that Scion serves exceptionally large monorepos and is not a general-purpose git replacement.
Why it matters: The comparison illustrates how assuming continuous server access changes source control architecture, connecting on-demand file retrieval and server-side operations to the infrastructure demands of agent-generated code.
TechCrunch · AI34 Cerebras CEO Sees Personal AI Assistants at Home as Near-Term Future
Cerebras CEO and co-founder Andrew Feldman said at TechCrunch Disrupt 2026 that a future with AI appliances in people’s homes is “not very far away.” He predicts personal AI assistants will run partly on device and partly in the cloud, learn about their users, and have access to credit cards to make purchases.
宝玉 · XPicks76 How Gemini 4 Argon Built a Japanese Temple Complex in Blender
Baoyu describes a demonstration in which Gemini 4 Argon used Antigravity to build a Japanese temple complex in Blender from one prompt containing a detailed workflow. The prompt referenced a scene-building skill document and requested architectural plans, four Nano Banana reference images, and coordinated agents that checked renders against those references and iteratively revised the scene. The demonstrator requested animation and programmatically generated bell sounds and ambient audio the next day, making those later additions to the initial modeling workflow.
Why it matters: The workflow offers a transferable approach to complex 3D generation by combining construction rules, visual references, agent coordination, and repeated comparison of rendered results.
宝玉 · X60 BaoCut 3.5 integrates Qwen Image 2.1 Turbo for local image generation
BaoCut 3.5 integrates Qwen Image 2.1 Turbo, letting you generate images locally without going through a server. On my Mac Mini M2, a 1080 image takes about 3-5 minutes, while 2K takes nearly 20 minutes. I also did not expect it to generate NSFW images directly 😅 An Agent can call the local image generation service. Fully open source and free: https://github.com/jimliu/baocut Download: http://baocut.com
The Verge · AIPicks76 Shopify opens its catalog up to more AI agents
Shopify announced Tuesday that shoppers will soon be able to configure any AI agent to browse and purchase from over a billion catalog listings without a partnership integration. Customers connect an agent to their Shop account and check out using Shop Pay within the conversation, with orders routed back to the Shop app. Shoppers can set rules such as budget limits or fast shipping preferences, but must approve each purchase.
Why it matters: The expansion moves agent shopping beyond individual partnership integrations, while requiring approval for each purchase gives customers a defined point of control over transactions.
AWS Machine Learning BlogPicks62 Building Agents That Transact With Anchor Browser and AgentCore Payments
The guide explains how Anchor Browser integrates with Amazon Bedrock AgentCore payments to handle x402-protected pages and APIs within the same browser session. Setting session.x402 to true enables automatic payments subject to configured spending and expiration limits, while wallet credentials remain outside the agent runtime. Existing browser automation code can continue unchanged; rejected payments or unsupported challenges leave the original HTTP 402 response intact.
Why it matters: The integration illustrates a transferable architecture for paid agent workflows by placing payment signing and budget enforcement outside the agent runtime while preserving browser session context.
宝玉 · X71 Yetone’s Magpie Maintenance Workflow Uses Three Claude Code Loops
Baoyu describes yetone’s workflow for maintaining Magpie with Claude Code and the official Opus 5.5 model, running three parallel /loop tasks for GitHub and Discord activity, X feedback, and code cleanup and lessons learned. Yetone says he spends a little time each evening handling mainly UI/UX issues. Supporting practices include reproducing bugs on Mac, Windows, and Linux, filtering irrelevant posts with a cheaper decision model such as Jev, and consulting stored memories and design documents to guide decisions.