-
github · 2026-08-29 · GitHub / MCP server stars:>100 / TypeScript
语言:TypeScript；stars:101；更新:2026-08-29T01:21:31Z
-
ithome · 2026-08-29 · 科技产品 / rss
IT之家 8 月 29 日消息，Meta 宣布推出一款名为 Meta XR Operator 的实验性开发者工具，旨在让 AI 智能体测试 VR 应用，目前相应工具已集成在 Meta XR SDK v205 中，便于开发者调用。 Meta 表示，相应工具中的 AI 智能体可以基于开发者项目自主启动、截取画面、发现问题、修改代码并再次验证修复结果，从而形成完整的“构建 — 测试 — 验证”流程，这样开发者就不需要进行繁琐的摘下 / 戴上头显调试过程。 除了快速迭代调试外，XR Operator 还支持利用自然语言进行命令控制。开发者只需描述测试场景，AI 智能体就能自动执行测试，并通过截图等证据返回测试通过或失败的结果。 不过，XR Operator 目前还无法听取应用中的音频效果，亦无法准确评估动画运动效果及细微的视觉缺陷，因此 Meta 建议优先用于“静态且确定性较高的场景”。
-
github · 2026-08-28 · GitHub / LLM workflow stars:>300 / JavaScript
语言:JavaScript；stars:401；更新:2026-08-28T23:46:15Z
-
github · 2026-08-29 · GitHub / Claude Code stars:>50 / Go
语言:Go；stars:967；更新:2026-08-29T01:25:13Z
-
github · 2026-08-29 · GitHub / LLM workflow stars:>300 / TypeScript
语言:TypeScript；stars:153775；更新:2026-08-29T01:24:11Z
-
github · 2026-08-28 · GitHub / LLM workflow stars:>300 / Python
语言:Python；stars:618；更新:2026-08-28T21:38:56Z
-
ifanr · 2026-08-26 · 明日产品 / rss
会让英伟达不开心 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
-
techcrunch-ai · 2026-08-27 · AI行业 / rss
At TechCrunch Disrupt 2026, the AI Stage is back to dig into the single hottest topic in the community for the past few years, presented by Google for Startups.
-
techcrunch-ai · 2026-08-28 · AI行业 / rss
Sandhya Devanathan will oversee some OpenAI operations across Southeast Asia and Australia in her new role.
-
techcrunch-ai · 2026-08-27 · AI行业 / rss
Zoph, who co-founded Thinking Machines Lab alongside Mira Murati and also served as the startup's CTO, led a brief stint at OpenAI and is now at Google.
-
techcrunch-ai · 2026-08-27 · AI行业 / rss
Some of the world's largest tech companies and AI startups have come together to decry the current state of cybersecurity and to advertise a new solution that they say can ward off a new generation of cyber threats.
-
techcrunch-ai · 2026-08-27 · AI行业 / rss
The updates indicate that Google is looking to position AI Mode as an AI travel agent of sorts, as it's moving beyond simply helping users find information to actually handling parts of the trip-planning and booking process.
-
ai-news · 2026-06-06 · main_news / Security / LLM
针对防不胜防的 Prompt Injection，OpenAI 搞了个 Lockdown 模式。虽然官方也承认这玩意不能 100% 免疫攻击，但至少能大幅降低敏感数据在注入攻击中被窃取、外泄的概率。 启发:提示词注入现在已经是 LLM 应用落地的头号大坑。加了层护城河是好事，但也变相说明了目前无论大厂小厂，模型本身的指令遵循和安全边界依然脆弱，现阶段还得靠硬核打补丁。
-
hf-papers · 2026-08-25 · AI论文 / hf-daily-papers / [object Object]
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded reward signals. The success of code agents illustrates why this matters. As code is executable, compilers and runtimes can provide high-quality rewards for Reinforcement Learning (RL) post-training of LLMs. By contrast, spatial generation still relies largely on fuzzy proxies such as CLIP scores. These signals are fuzzy and biased, making them hard to support RL post-training. Compared with these, game development provides a missing reward environment for spatial world models. A scene encoded by a game engine is an executable world specification: the engine can efficiently check collision, physics, navigability and bounded playability, while the developer provides the global verification signal by judging whether the scene should be accepted. Game development also provides real-world long-horizon trajectory data for RL post-training. We therefore propose Reinforcement Learning with Human-Engine Verification (RLHEV), a post-training paradigm that combines dense engine signals with implicit human acceptance feedback from the development process.
-
ai-news · 2026-06-06 · finance_news / AI 基础设施 / 能源
特锐德推出了专供智算中心的模块化供电站“算电岛”，不仅能直供 800V 直流机房，官方号称配合 AI 优化调度，能让 Token 的综合用电成本直接砍掉约 30%。 启发:算力的尽头是电力。国内这种卷底层基建的降本思路非常实在，毕竟现在大模型拼到最后，拼的就是显卡折旧和电费谁能省下来。
-
hf-papers · 2026-08-26 · AI论文 / hf-daily-papers / [object Object]
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent architectures do not fully support this goal. Single-agent self-correction combines task execution and trajectory assessment within one context, while subagent delegation separates execution but typically cannot redirect an active subagent. We present PILOT, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-evolution distils procedures and failure modes revealed during execution into reusable skills and memory. Across two frozen backbones and three benchmarks, PILOT ranks first in five of six configurations. On Terminal-Bench 2.0, PILOT outperforms counterpart harnesses by up to 9.8 percentage points. In the self-improvement setting, PILOT gains 14.6 points with GLM-5.1 and 12.4 points with Kimi-K2.6. Mean output tokens fall by 42.9% and 47.4%, while successful evaluations per million output tokens rise by 110.3% and 134.0%, respectively.
-
hf-papers · 2026-08-25 · AI论文 / hf-daily-papers / [object Object]
Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a user could edit. To address this, we explore the paradigm of 3D shape as code, leveraging and scaling the coding ability of an LLM for 3D modeling. We introduce Procedura, a novel 3D modeling agent framework that writes an object as a procedural assembly, a parametric program whose named parts are joined by typed, machine-checkable mates. From a text prompt, the agent plans the object as an assembly graph and writes the program part by part, solving each placement from the mated frames rather than guessing it, and admitting a part only once compile, mate, and connectivity checks pass. A decoupled vision critic then refines the assembly one diagnosed fix at a time. Moreover, the same graph carries per-part materials and a simulator-validated articulation. We evaluate on P3D-Bench under its assembly judge, and with the same judge on MechBench-36, our hard-surface benchmark. On both, Procedura outperforms state-of-the-art native 3D generators and every prior 3D-code agent on judged quality, produces the sharpest edges of any method we evaluate, and is the only one whose output is an editable, part-structured program.
-
hf-papers · 2026-08-21 · AI论文 / hf-daily-papers / [object Object]
AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas, prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy Distillation restores generalization lost during SFT; and HSA-RL improves robustness to changing Harnesses through reinforcement learning in augmented environments. Across four evaluation sets, HAT achieves 94.8 on Live-Stream QA (base: 80.3; strongest general LLM: 93.0) and 94.6 on Harness-Variant QA (base: 75.4). Unlike Fixed-Harness SFT, which lowers IFEval by 7.7 points from the base model, HAT avoids this regression and reaches 83.5. On one NVIDIA H20 GPU, the optimized system delivers P50 and P95 latencies of 3.4 s and 8.1 s. Deployed in Taobao Live's digital-avatar service, it also yields positive online A/B test results for GMV and item-page views.