Archive
Agent、MCP、coding agent、工作流自動化與評測。
AI 安全
AWS proposes invoking Bedrock Guardrails separately on model input, tool parameters, and tool output, closing gaps left when only prompts and responses are inspected. The example supports tool-specific rules but provides no latency, false-positive rate, or security evaluation for structured actions.
代理工具
Switch 把 Slack、Teams、Discord 等頻道映射至共享房間，讓 Codex、Claude Code 與其他代理保留共同上下文。程式碼可自行部署，但 Commons Clause 限制商業轉售，且成本防護與部分安全控制尚未完成。
代理工具
ASIL lets agents read software state as JSON, then execute semantic actions through file parsers, native scripts, or service APIs. It significantly outperformed screen control across 380 tasks, but the comparison changed both the information visible to the agent and the granularity of its actions, so the results cannot be interpreted simply as an improvement in model capability.
代理工具
The Model Hardware Standard abstracts device state and operations into discoverable primitives such as `read` and `write`, which can be orchestrated through MCP, a CLI, or programmatic interfaces. It has been used with liquid handlers, robotic arms, and quantum-computer lasers, but its specification and code remain unpublished, while the security evidence comes mainly from partner proofs of concept.
最新模型
Google has moved its conversational video model into general availability, adding first-and-last-frame interpolation, scene extensions of up to 40 seconds, and four resolution settings. The new interface provides greater workflow control, but both 1080p and 4K are produced through upscaling, while complex motion and text consistency remain limited.
最新模型
The new shared task requires systems to localize and classify visual language model hallucinations character by character, rather than merely judging whether an entire response is trustworthy. Twenty-seven teams submitted more than 600 systems, but the closed test set and unstable adjacent rankings limit the conclusions that can be drawn.
代理工具
Researchers used 441 enterprise repositories to develop the four-level Repository AI Maturity Profile, then reanalyzed 509 open-source projects that had adopted coding agents. Repositories with shared rules or agent configurations showed better quality metrics, but the observational study cannot establish that the configuration files themselves caused the improvements.
最新模型
IBM has released three Apache 2.0-licensed dense models in 3B, 8B, and 30B sizes, featuring switchable reasoning modes and native tool calling. The 8B and 30B models additionally underwent agentic reinforcement learning in codebase, terminal, and search sandboxes, although IBM’s official materials provide inconsistent accounts of their foundational training lineage.
硬體
OpenAI has published the first benchmark results for its in-house inference ASIC, which uses a single accelerator architecture for both prefill and decode. SemiAnalysis observed and verified the testing process on site, but the data was still supplied by OpenAI, while production silicon and AgentX results have yet to be validated.
最新模型
Google has introduced two speech-to-text endpoints featuring automatic language detection, custom vocabulary biasing, and smart formatting. The non-streaming model is more accurate, while the real-time version does not support speaker diarization or word-level timestamps.
AI 安全
Researchers trained automated alignment auditors using hidden behaviors, pairwise rewards, and calibration on normal models, raising the best configuration’s aggregate score from 44.2 to 48.7. The experiments also show that directly rewarding the “discovery of suspicious behavior” encourages fabricated evidence, meaning deployed auditing agents cannot optimize solely for detection rate.
機器人與具身 AI
GigaAI has released GigaBrain-0.7’s base weights, training pipeline, and robot deployment examples. The model was pretrained on 37,300 hours of heterogeneous embodied data. However, the paper’s three-system architecture and leading results are not yet fully reproducible, and the official evaluation code remains on the roadmap.