#77
OpenAI 发布 GPT-6 Astra 提示词指南，含 slop 词屏蔽清单
OpenAI 在模型文档中说明 GPT-6 Astra 相比 GPT-5.6 Sol 更常提出澄清问题、对上下文更敏感，并给出让模型更主动、审计 AGENTS.md 等技能文件、控制写作风格、约束子智能体委派和测试规模的提示词建议。
推荐理由OpenAI 在模型文档中说明 GPT-6 Astra 相比 GPT-5.6 Sol 更常提出澄清问题、对上下文更敏感，并给出让模型更主动、审计 AGENTS。
Pai 的 AI 雷达
今天的简报围绕“代理正在如何工作、被评估和治理”展开：从 agent-sessions、前沿模型的 AEO 选择与应对，到数学代理作弊、Agent 线上 Badcase 和不确定性闸门，再延伸至 ChatGPT 与 Gemini 的流量变化、内容产品与独立新闻支持；同时夹带视频压缩、地图投影、洛杉矶城市演化和 MovieMaker 等可直接动手或轻松浏览的技术小品。阅读时可先把前半部分当作一组关于 Agent 可靠性、分发与社会影响的连贯线索，再用后半部分的工具、可视化和旧邮件案例换气，最后回到“如何在不确定中使用 Agent”这一实践问题。
OpenAI 在模型文档中说明 GPT-6 Astra 相比 GPT-5.6 Sol 更常提出澄清问题、对上下文更敏感，并给出让模型更主动、审计 AGENTS.md 等技能文件、控制写作风格、约束子智能体委派和测试规模的提示词建议。
Reasoning allows artificial intelligence models to revisit and correct their mistakes, enabling recent frontier advances in mathematical theorem solving, software engineering, and autonomous task planning. Reasoning models are widely observed to reason for longer on harder tasks,
While diffusion-based methods have recently emerged as effective tools for probing the intrinsic geometry of high-dimensional data, their statistical difficulty remains largely unexplored. We study estimation of the finite-scale population functional underlying FLIPD (Kamkari et
Recently, multimodal large-scale reasoning models have demonstrated remarkable capabilities in solving complex tasks through long Chains-of-Thought (M-CoT). However, excessively long reasoning trajectories incur substantial computational costs and significant KV-cache pressure. E
I built WarLightning, a browser-based fighter jet combat game. You can: Fly different fighter jets Dogfight AI aircraft Fire air-to-air missiles Bomb ground targets Fly around large maps Choose aircraft from a hangar It's still very much in development, and I'm trying to figure o
Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile, frequently exhibiting reasoning and coordination errors that can lead to system-level failures. Failure attribution in such syst
OpenAI acknowledged its role in a recently reported incident where AI agents took over a German wiki forum.
LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a system, diagnose errors, or decide when to escalate an output. Such use assumes
LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a system, diagnose errors, or decide when to escalate an output. Such use assumes
As a potent greenhouse gas, methane is a major driver of climate change. Its effective mitigation relies on timely detection. Conventional detection methods rely on orthorectification to correct geometric distortions and matched filters to enhance plume signals, which are steps d
Repository-scale refactoring requires coding agents to propagate a single change across many interdependent files without altering program behavior, yet to our knowledge no existing harness isolates the design choices that determine agent success on this task. We present Refactor
So I was learning Python coding with Claude. When I had a good grasp of 3Sum, Claude asked me to create an example, and I was too lazy to do it. So I asked Chatgpt to create one. then I don't know how Claude could detect that this is chatgpt
Four-dimensional (4D) flow magnetic resonance imaging (MRI) is a powerful non-invasive technique for visualizing and quantifying complex blood flow patterns in vivo. Despite its clinical promise, broader adoption is limited by low spatial resolution and sensitivity to noise, whic
Improving an industrial recommender is an iterative research-and-engineering process rather than a direct path from idea to deployment. In \textbf{DASHEN, NetEase's gaming-community app}, algorithm engineers typically identify promising directions from research papers, technical
Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either treat audio as an auxiliary component of video quality or assess it in isolation from audiovisual grounding, making it difficult to d
As vision-language models (VLMs) rapidly advance in image understanding, cross-modal reasoning, and complex instruction execution, instruction-following capability has become a key indicator of their reliability and practicality. However, existing multimodal instruction-following
Background. Large language models (LLMs) are being adopted in biomedical research at a rapid and accelerating pace, yet commercial services that host many widely used models operate under deprecation schedules that can complicate scientific reproducibility. Methods. We searched P
Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's health over time, enabling timely diagnosis, personalized treatment, and early detection of critical events. However, the development of clinically reliable and linguistically inclusive
Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override reliable predictions. One-shot communication sharpens this te
Personalized federated learning (PFL) is a promising paradigm for collaborative learning over distributed devices, where edge nodes collaboratively train personalized models without sharing raw data. Although PFL addresses data heterogeneity by learning client-specific models, it
Although automatic text simplification (ATS) is critical for accessibility, its progress has not matched the rapid evolution of broader natural language processing techniques. This paper investigates the application of reinforcement learning (RL) to improve the quality of ATS for
This paper addresses navigation by composite heterogeneous robots in a decentralized system when policy reasoning and local control operate at different update levels. In a NetLogo--Python implementation, three robots share motion dynamics but use different LLM backends. Each rob
Synthetic medical time-series generation can alleviate data scarcity and support the development of reliable clinical prediction models. However, existing methods mainly focus on matching the overall distribution and temporal dynamics of real data, which does not necessarily ensu
Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural language across hours-to-days observation horizons. Existing systems either drop fine-grained motion (clip-level video-langu