Archive
1526 technical news articles
代理工具
AWS has released a CDK-deployable restaurant agent example in which three isolated runtimes share the same memory and MCP backend tools. The voice path uses Nova 2 Sonic for speech-to-speech processing directly, but WebRTC, TURN, identity linking, and fixed networking costs still require independent governance.
AI 安全
Microsoft has uncovered phishing emails that insert invisible Unicode Tag characters into financial keywords, altering the tokens seen by rule-based and machine-learning classifiers. With attacks peaking at more than 2.3 million emails per day, the campaign shows that AI red-teaming techniques are beginning to migrate into conventional cybersecurity offense and defense.
代理工具
The new `langchain.mcp` uses FastMCP to unify connections, authentication, and protocol negotiation, replacing the standalone adapter package. Servers can request additional information or approval during tool execution, while LangChain maps the pause point to a resumable LangGraph interrupt.
AI 安全
Malicious projects can place commands in `.git/config` under `core.fsmonitor`, then wait for an agent to run `git status` or `git diff` in the background to execute them on the host. Some products have been patched, but the incident shows that tool approvals can still be bypassed by underlying programs if an agent’s sandbox does not cover startup and version-control processes.
推論系統
SGLang Simulator intercepts runtime components on the CPU to simulate scheduling, batching, and multi-tier KV caches without actually loading models or executing GPU kernels. The team claims errors below 5% on key metrics for two Qwen3 models running on H20 GPUs, but hardware and model coverage remain limited.
GitHub Repo
Truespar has released Paddock’s scheduler, paged KV cache, memory management, and custom CUDA kernels, along with OpenAI- and Anthropic-compatible interfaces. The authors’ benchmarks show it outperforming vLLM and SGLang on some single-GPU workloads, but the results have not been independently reproduced, and Paddock does not support tensor parallelism, ROCm, or Metal.
代理工具
A team from IBM Research and Carnegie Mellon University enables a judge model to generate rubrics for each set of trajectories, then redistributes the overall reward to the relevant steps. The method improves performance on AppWorld by 15.9 percentage points, although its correctness still depends on model judgments that have not been manually validated.
最新模型
OpenAI’s new flagship model can continue reasoning while tools run in the background and receive mid-execution corrections over WebSocket. Its stronger agentic capabilities come with new migration constraints—and the first Critical rating for cybersecurity capabilities.
代理工具
The new release lets applications interrupt responses when users speak over them based on the number of audio bytes actually played, while keeping conversation state in sync. It also adds an out-of-band prompt queue and an event-listening interface, so realtime agents no longer need to disguise every control signal as a user turn.
推論系統
The new release adds `--lazy-mode`, a quantization working-memory limit, and row-slab streaming, eliminating the need to load extremely large tensors into RAM all at once. It also introduces preliminary support for Qwen3.8-Flash-Next and Nemotron-3-Puzzle, though performance optimizations and compatibility with some hardware remain incomplete.
代理工具
The new `/skill-doctor` command lists unused skills and their context footprint, helping developers identify prompt costs paid repeatedly on every turn. The update also expands dangerous deletion detection, fixes context loss during session restoration, and treats public chart URLs containing embedded content as external uploads.
AI research
Researchers found that repeatedly sampling from a single query while giving the student model token-level teacher supervision can, after 300 steps, cover 71.5% of the state reached by full-data training. Adding 16 semantically diverse queries raises coverage to 98.9%, though the findings remain limited to the specified small models, teachers, and benchmarks.