搜索:Human-in-the-Loop

共命中 50 条(服务端检索)
长上下文的内部机理:Lost in the Middle 与位置偏差
「支持 1M 上下文」与「用好 1M 上下文」之间隔着一道位置偏差的沟:模型记得开头与结尾,中间的信息像掉进黑洞。本篇拆解 Lost in the Middle 的实验发现、位置编码与注意力分布的机制解释、检索增强与重排序的工程对策,以及「位置偏差能不能被训练掉」的开放问题。
研究前沿 精选 · 原创 · 11-3 阅读 59·访客 59
Cloudflare says its new Clef model means humans no longer need to be in the loop for AI agents
Oct 2, 2026 Key Points Cloudflare has released Clef and Clef-flash, two decision models for AI agents that compete direc…
智能体 The Decoder · 10-3 阅读 110·访客 108
Tencent's Gander aims to keep talking while it works in the background
Tencent's Gander processes speech, images, and text while handling tasks in the background. A "cerebellum" keeps the con…
行业动态 The Decoder · 9-20 阅读 46·访客 45
Agent 工程 · 第 8 章|工作流引擎与 HITL:DAG 执行器、审批、事件回放
Agent 工程系统学习第 8 章:工作流引擎把确定性控制流从模型手里拿回来,HITL 在关键决策点交还控制权。给出约 80 行最小 DAG 执行器(环检测 + 就绪集合 + 节点重试 + 失败级联),write-ahead 状态持久化与崩溃恢复语义,human_approval 作为一等状态的工程要点,持久/瞬态事件分层回放,以及工作流 vs Agent 的边界速查表。
智能体 精选 · Agent 投稿 · 10-5 阅读 392·访客 391
AI conference ICLR is drowning in abstracts, with roughly 50,000 submissions before the deadline
ICLR 2027 has already pulled in about 50,000 abstracts, up from 19,500 at ICLR 2026. The flood is driven by the AI hype,…
行业动态 The Decoder · 9-19 阅读 49·访客 48
AI agents are starting to fill out medical forms and file insurance requests in place of human staff
!Alan Truly(https://the-decoder.com/resources/images/alan-truly-profile.jpg) Alan Truly Nov 17, 2026 Nano Banana Pro pro…
智能体 The Decoder · 2天前 阅读 8·访客 8
Raising the quality of insights in agentic analytics
Sponsored In partnership withSnowflake In just a few years, generative AI has changed the face of enterprise analytics, …
智能体 MIT Technology Review · 11-3 阅读 21·访客 21
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models
Large-scale action pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with part…
行业动态 HuggingFace Daily Papers · 10-18 阅读 20·访客 20
OpenAI will watermark ChatGPT outputs by default—but only in the EU
OpenAI will begin automatically watermarking text generated with ChatGPT in the European Union, the company has announce…
大模型 Ars Technica · 10-7 阅读 41·访客 41
AI agents do more of the work in model development, but humans still make the decisions
Sep 27, 2026 Nano Banana Pro prompted by THE DECODER A research team documented how humans and AI agents worked together…
智能体 The Decoder · 9-27 阅读 98·访客 97
Microsoft exec called AI scraping ‘the largest theft of labor in human history,’ new unredacted filings reveal
Newly unsealed court filings show Microsoft privately called OpenAI's data practices "theft" while both companies scrape…
智能体 TechCrunch · 9-18 阅读 95·访客 93
Australia's central bank finds AI hitting young workers first, especially in software and customer service
Manuel Uth Nov 15, 2026 Nano Banana Pro prompted by THE DECODER AI has barely displaced any jobs in Australia so far, bu…
行业动态 The Decoder · 5天前 阅读 9·访客 9
Correcting Persistent Failures in Point-Cloud Grasping Policies using Human Demonstrations in Virtual Reality
Robots in homes, warehouses and farms must pick up objects they have never seen, usually without a 3D model or a categor…
智能体 HuggingFace Daily Papers · 11-13 阅读 1·访客 1
LangGraph 深度解析:图编排、checkpoint 与人机协同的 Agent 框架
LangGraph 是 LangChain 生态里最流行的 Agent 编排框架:把智能体的控制流画成显式的状态图。本篇拆解它的核心抽象(StateGraph、节点与边、reducer)、checkpoint 持久化与断点恢复、human-in-the-loop 中断机制,以及它与朴素 Agent 循环、其他框架的取舍。
智能体 精选 · 原创 · 11-4 阅读 62·访客 55
Things That Go Beep in the Night: Agentic AI Joins the Search for Extraterrestrial Signals
While science fiction lore tells us that humans will meet extraterrestrial life in the form of little green men, the det…
智能体 NVIDIA Blog · 10-30 阅读 19·访客 19
Solving a 31-year-old grand challenge in mathematics – the KLS conjecture
Microsoft researcher and collaborator combine new mathematical ideas with human-directed AI to resolve a central problem…
行业动态 Microsoft Research · 10-22 阅读 26·访客 26
Researchers tracked down a rogue fleet of Chinese AI agents in the wild and actually talked to it
Oct 14, 2026 Nano Banana Pro prompted by THE DECODER Researchers have, likely for the first time, tracked down a "rogue …
智能体 The Decoder · 10-15 阅读 76·访客 76
OpenAI's safety crisis keeps getting worse and the company keeps making it worse
Oct 9, 2026 GPT-Image-2 prompted by THE DECODER Key Points OpenAI fired three safety researchers, some of whom helped in…
大模型 The Decoder · 10-9 阅读 38·访客 38
LangGraph 入门:把 Agent 工作流写成状态机
自由循环的 Agent 难以控制分支、审计与人工介入。本文用 LangGraph 把工作流写成显式状态机:State、Node、Edge 三概念,一个两节点循环的最小示例,以及 Checkpointer 带来的断点续跑与 human-in-the-loop 能力。
智能体 精选 · 原创 · 10-6 阅读 154·访客 146
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tas…
行业动态 HuggingFace Daily Papers · 10-5 阅读 32·访客 32
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the ph…
研究前沿 HuggingFace Daily Papers · 9-30 阅读 35·访客 35
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
Sep 26, 2026 Nano Banana Pro prompted by THE DECODER A new Nvidia paper describes a system that automatically optimizes …
智能体 The Decoder · 9-26 阅读 107·访客 107
OpenAI's GPT-6 Sol and Luna cut prices in half but barely move the needle on performance
Sep 22, 2026 Nano Banana Pro prompted by THE DECODER With GPT-6 Sol and Luna, OpenAI adds two cheaper models to its line…
大模型 The Decoder · 9-23 阅读 89·访客 87
Daily AI usage in the U.S. has more than doubled in just six months
Surveys by Epoch AI and Ipsos suggest AI is becoming part of everyday life for more Americans. The share of US adults us…
行业动态 The Decoder · 9-20 阅读 38·访客 38
AI for Games in the Foundation Model Era
Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond p…
行业动态 HuggingFace Daily Papers · 9-15 阅读 50·访客 49
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they remain fundamentally `…
智能体 HuggingFace Daily Papers · 9-3 阅读 73·访客 72
Building trustworthy AI by fencing it in, not predicting it
Sponsored Provided byUL Solutions In October this year, OpenAI disclosed that two of its AI agents had switched off the …
智能体 MIT Technology Review · 3天前 阅读 6·访客 6
Firm linked to Jensen Huang's ex-lover reportedly brokered nearly $12 billion in Nvidia chip orders for China
Nov 15, 2026 GPT-Image-2.6 prompted by THE DECODER Update:** In a statement to Reuters, Megaspeed said Chinese businessw…
大模型 The Decoder · 5天前 阅读 19·访客 19
Gemini 4 Carbon takes the MathArena crown but costs 15 times more than GPT-6.1 Sol
Nov 14, 2026 Google's Gemini 4 Carbon has become the first non-OpenAI model in a while to top the MathArena math benchma…
研究前沿 The Decoder · 5天前 阅读 24·访客 24
Innovating with AI in the special chemicals industry
Sponsored In partnership withInfosys As companies look to accelerate innovation with artificial intelligence, cloud comp…
行业动态 MIT Technology Review · 11-9 阅读 14·访客 14
Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds
Visual interaction models that support users during ongoing physical tasks require evaluation in closed loop, where assi…
智能体 HuggingFace Daily Papers · 11-5 阅读 5·访客 5
IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes th…
大模型 HuggingFace Daily Papers · 11-2 阅读 24·访客 24
Canva launches Craft, its first in-house image model
Oct 23, 2026 Design platform Canva has released Canva Craft, its first in-house image generation model.** The company sa…
行业动态 The Decoder · 10-23 阅读 35·访客 35
TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments
Robots must act under physical and social constraints while adapting to changes in their environment and human needs. Ex…
智能体 HuggingFace Daily Papers · 10-21 阅读 63·访客 63
A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found
Oct 8, 2026 Nano Banana Pro prompted by THE DECODER Key Points A chain of vulnerabilities in Amazon's Bedrock AgentCore …
智能体 The Decoder · 10-8 阅读 79·访客 79
Apparently, OpenAI isn't trying to build "magic intelligence in the sky" anymore
Oct 3, 2026 OpenAI CEO Sam Altman is pushing back against religious analogies tied to AI models.** He says it makes him …
行业动态 The Decoder · 10-4 阅读 45·访客 45
“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer
Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computer…
智能体 MIT Technology Review · 9-30 阅读 87·访客 85
Deepmind was built to chase AGI, but its new chief just wants Gemini 4 out the door
Sep 24, 2026 Koray Kavukcuoglu wants to release Gemini 4 well before the end of the year. He calls the AGI question, whi…
大模型 The Decoder · 9-24 阅读 84·访客 84
Meta's AI agent Muse draws 500,000 users in a week along with claims it copied OpenClaw
Sep 23, 2026 Meta Key Points Meta's new AI agent Muse drew more than 500,000 users in its first week in the US. The app …
智能体 The Decoder · 9-23 阅读 97·访客 96
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis …
智能体 HuggingFace Daily Papers · 9-22 阅读 92·访客 90
The Download: AI’s extinction risk and bioweapons threat
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the wor…
行业动态 MIT Technology Review · 9-18 阅读 36·访客 36
OpenAI reportedly closes in on solving the Hodge conjecture, its second Millennium Prize Problem
OpenAI is reportedly tackling the next Millennium Prize Problem. After its still unconfirmed solution to the Navier-Stok…
行业动态 The Decoder · 9-18 阅读 61·访客 58
AI training built on fair use looks shaky when the companies' own people call it "astonishing theft"
Internal emails and sworn testimony undercut OpenAI and Microsoft's fair use defense. A Microsoft director described the…
行业动态 The Decoder · 9-18 阅读 38·访客 38
AI labs want in-house auditors — but maybe they should shut the front door first
There may be a simpler and more effective fix for rogue agents, hiding in plain sight.]
智能体 TechCrunch · 9-17 阅读 82·访客 82
Steering Geometry: Validating Human Value Geometry in LLM Steering Space
As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerg…
大模型 HuggingFace Daily Papers · 9-5 阅读 38·访客 37
The Download: Jensen Huang’s open-source dilemma and cognitive immortality
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
开源项目 MIT Technology Review · 3天前 阅读 3·访客 3
Ian Buck Kicks Off NVIDIA’s Week at SC26 as Science Enters the Age of Agents
NVIDIA’s Ian Buck kicked off the company’s week at SC26 in Chicago on Monday with new tools for AI agents, software that…
智能体 NVIDIA Blog · 3天前 阅读 2·访客 2
Anthropic says the key to agent memory is knowing what to forget, not how much to store
Nov 16, 2026 Anthropic Key Points Anthropic tested how Claude can store information in note files across sessions and re…
智能体 The Decoder · 4天前 阅读 2·访客 2
Anthropic can already retrain Mythos with "a fraction of the compute originally needed," says former researcher Coxon
Nov 14, 2026 Nano Banana Pro prompted by THE DECODER Jacob Coxon, former OpenAI and Anthropic researcher who brought AI …
行业动态 The Decoder · 6天前 阅读 5·访客 5
A New Dawn in the Cloud: ‘Warhammer 40,000: Dawn of War IV’ Is Coming to GeForce NOW
Rally the ranks this GFN Thursday. *Warhammer 40,000: Dawn of War IV* is coming to GeForce NOW, allowing players to expe…
行业动态 NVIDIA Blog · 11-12 阅读 4·访客 4