发布日期:2026-08-09
收录条目:19
1. Meet Shepherd: An Open-Source Python Substrate That Lets Meta-Agents Fork, Replay, and Revert Any Agent Run
- 来源:MarkTechPost
- 发布时间:2026-08-08 20:54 UTC
- 链接:https://www.marktechpost.com/2026/08/08/meet-shepherd-an-open-source-python-substrate-that-lets-meta-agents-fork-replay-and-revert-any-agent-run/
摘要:Long agent runs accumulate state that no transcript records — edited files, a live dev server, installed packages, a warm prompt cache. When an agent misreads a traceback at step 10 and rewrites a correct file, patching
2. An Amazon data center could have the worst polluting power plant in the country
- 来源:The Verge AI
- 发布时间:2026-08-08 17:53 UTC
- 链接:https://www.theverge.com/ai-artificial-intelligence/977124/amazon-data-center-worst-polluting-power-plant
摘要:To power its new West Texas data center, Amazon is investing in the construction of a new power plant that could be one of the largest single producers of greenhouse gases in the US, according to the New York Times. The
3. Pokee AI Releases Pokee-Isaac 28B: A 10M-Token Context Agentic Model Built to Run Inside the Customer Boundary
- 来源:MarkTechPost
- 发布时间:2026-08-08 17:04 UTC
- 链接:https://www.marktechpost.com/2026/08/08/pokee-ai-releases-pokee-isaac-28b-a-10m-token-context-agentic-model-built-to-run-inside-the-customer-boundary/
摘要:Pokee AI released Pokee-Isaac 28B, a 28B text-only foundation model with a 10M-token context window built to run inside the customer boundary. It scores 93.3% on RULER at 10M tokens, where every baseline in its compariso
4. Designing Scalable Interactive Visualizations with Reflex XY: Composition, Million-Point Rendering, Streaming, Custom Marks, and Export
- 来源:MarkTechPost
- 发布时间:2026-08-08 09:42 UTC
- 链接:https://www.marktechpost.com/2026/08/08/designing-scalable-interactive-visualizations-with-reflex-xy-composition-million-point-rendering-streaming-custom-marks-and-export/
摘要:Dive into the advanced visualization capabilities of the Reflex XY Python library. This tutorial guides you through building high-performance, interactive charts—from handling million-point datasets and real-time streami
5. Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size
- 来源:MarkTechPost
- 发布时间:2026-08-08 04:36 UTC
- 链接:https://www.marktechpost.com/2026/08/07/mistral-ai-releases-shieldstral-1-0-3b/
摘要:Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that frames content moderation as a single yes/no question instead of a fixed harm taxonomy. Operators supply the
6. Tencent Cloud Open-Sources TencentDB Agent Memory v2.0: A Team-Level Memory Hub for AI Coding Agents
- 来源:MarkTechPost
- 发布时间:2026-08-07 21:52 UTC
- 链接:https://www.marktechpost.com/2026/08/07/tencent-cloud-open-sources-tencentdb-agent-memory-v2-0/
摘要:Tencent Cloud has open-sourced TencentDB Agent Memory v2.0, a team-level memory hub that turns conversations, documents and code into four governed, reusable assets — Chat Memory, Skill, LLM-Wiki and Code-Graph. It is MI
7. Building a Multimodal RAG Pipeline with NVIDIA NeMo Retriever, Hosted NIMs, LanceDB, Reranking, and Grounded Generation
- 来源:MarkTechPost
- 发布时间:2026-08-07 21:13 UTC
- 链接:https://www.marktechpost.com/2026/08/07/building-a-multimodal-rag-pipeline-with-nvidia-nemo-retriever-hosted-nims-lancedb-reranking-and-grounded-generation/
摘要:In this tutorial, we build an advanced multimodal retrieval-augmented generation pipeline with NVIDIA NeMo Retriever. We begin by configuring a Python 3.12 environment, installing the required packages, and performing of
8. NVIDIA AI Releases NOOA: An Object-Oriented Python Framework That Turns an AI Agent Into a Single Python Class
- 来源:MarkTechPost
- 发布时间:2026-08-07 20:42 UTC
- 链接:https://www.marktechpost.com/2026/08/07/nvidia-ai-releases-nooa-an-object-oriented-python-framework/
摘要:NVIDIA Labs has open-sourced NOOA (NVIDIA Object-Oriented Agents), a model-agnostic Python framework for building AI agents. Agent development today is split across prompt templates, tool schemas, callback code, and work
9. Fenix Flexin isn’t even denying using AI to make ‘Rubberz’ anymore
- 来源:The Verge AI
- 发布时间:2026-08-07 20:01 UTC
- 链接:https://www.theverge.com/ai-artificial-intelligence/976801/fenix-flexin-rubberz-ai-song-treblo
摘要:It took long enough, but now LA rapper Fenix Flexin appears to have admitted using AI for the 80s synth pop-themed song "Rubberz." His comments follow the producer Medasin's videos claiming that an AI tool called Treblo
10. Watching Roku’s AI channel is like eating from a trough
- 来源:The Verge AI
- 发布时间:2026-08-07 18:59 UTC
- 链接:https://www.theverge.com/entertainment/976939/roku-fairground-ai-fast-channel
摘要:The appeal of free ad-supported streaming television (FAST) channels has always been the way they make it easier to (re)discover classic films and series. But Roku's latest experiment in the FAST space has less to do wit
11. OpenAI puts the brakes on a new model because it’s supposedly too powerful
- 来源:The Verge AI
- 发布时间:2026-08-07 18:40 UTC
- 链接:https://www.theverge.com/ai-artificial-intelligence/976948/openai-astra-model-pause-critical-cyber-capabilities
摘要:OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure
12. What’s behind the Google AI shake-up
- 来源:The Verge AI
- 发布时间:2026-08-07 16:45 UTC
- 链接:https://www.theverge.com/podcast/976784/google-deepmind-ai-race-vergecast
摘要:Some of the biggest names on Google's AI team got new jobs this week. In some cases, including for legendary Googler Jeff Dean, those jobs are no longer at Google. Given that Google's models seem to be behind the best of
13. How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore
- 来源:AWS ML Blog
- 发布时间:2026-08-07 16:26 UTC
- 链接:https://aws.amazon.com/blogs/machine-learning/how-cohere-health-digitizes-clinical-policies-using-amazon-bedrock-agentcore/
摘要:In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through AgentCore Gateway, AgentCore Memory, and th
14. How TReNDS automates root-cause analysis with Amazon Bedrock
- 来源:AWS ML Blog
- 发布时间:2026-08-07 16:22 UTC
- 链接:https://aws.amazon.com/blogs/machine-learning/how-trends-automates-root-cause-analysis-with-amazon-bedrock/
摘要:TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates production errors in real time, reducing root-c
15. Determining playoff clinching scenarios in the NHL using constraint programming
- 来源:AWS ML Blog
- 发布时间:2026-08-07 16:21 UTC
- 链接:https://aws.amazon.com/blogs/machine-learning/determining-playoff-clinching-scenarios-in-the-nhl-using-constraint-programming/
摘要:The AWS Generative AI Innovation Center built an automated system that uses constraint programming and custom tree search to determine, with mathematical certainty, when and how an NHL team clinches a playoff spot. The a
16. Responding to the next frontier of critical cyber capabilities
- 来源:OpenAI News
- 发布时间:2026-08-07 15:20 UTC
- 链接:https://openai.com/index/responding-next-frontier-critical-cyber-capabilities
摘要:OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.
17. How HSP GRUPPE builds AI capabilities for tax advisory
- 来源:OpenAI News
- 发布时间:2026-08-07 09:00 UTC
- 链接:https://openai.com/index/hsp-gruppe
摘要:Discover how HSP GRUPPE uses ChatGPT Enterprise to boost productivity, improve work quality, and create more capacity for tax advisory and client service.
18. Microsoft Open Sources code-testing-generator: a Polyglot Unit-Test Agent That Hits 92.1% Task Completion Versus 78.9% for Stock Copilot
- 来源:MarkTechPost
- 发布时间:2026-08-07 05:42 UTC
- 链接:https://www.marktechpost.com/2026/08/06/microsoft-open-sources-code-testing-generator/
摘要:Microsoft has open sourced code-testing-generator, a polyglot unit-test agent shipping in the MIT-licensed dotnet/skills repository. It reads a repository before writing anything — detecting the language, test framework,
19. Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights
- 来源:MarkTechPost
- 发布时间:2026-08-07 03:42 UTC
- 链接:https://www.marktechpost.com/2026/08/06/liquid-ai-lfm2-5-2-6b-on-device-agentic-model/
摘要:Liquid AI released LFM2.5-2.6B, an agentic model that plans, calls tools, and completes multi-step tasks entirely on-device. The 2.69B parameter model pairs 22 double-gated short convolution blocks with 8 GQA blocks acro