Archive
1528 technical news articles
代理工具
Agno 3.0.6 introduces stateless MCP transport, allowing any replica to handle requests without session affinity. The framework also adds protocol version negotiation and a Server Card, but retains the legacy session-based mode as the default for compatibility with existing deployments.
向量資料庫與 AI 基礎設施
Qdrant 1.19.1 adds prefetching and batched SIMD to TurboQuant scoring while reducing extra allocations in HNSW search and the query plane. The release also strengthens fault recovery for shard transfers, but Qdrant has yet to publish comprehensive performance comparisons across different processors and datasets.
AI 輔助科學研究
Google Research, HHMI Janelia, and University of Cambridge researchers have completed a male fruit fly connectome spanning the brain and ventral nerve cord and containing more than 166,000 neurons. The data and query tools are publicly available, but a static wiring diagram from a single specimen still cannot directly explain neural activity or behavioral causality.
最新模型
Zhipu AI has unveiled GLM-5.3-Flash, a native multimodal model with 320B total parameters and 18B active parameters per token, releasing its weights under the MIT License. The new architecture is claimed to require three times less attention computation and 4.4 times less KV cache than GLM-5.3, but “Flash” does not mean it can be easily deployed on a typical workstation.
推論系統
Uno attaches lightweight diffusion weights to an autoregressive LLM, then uses Ψ-Spec to propose multiple tokens at once while preserving the original model’s sampling distribution. The authors report speedups of up to 3×, though the current figures are limited to the research team’s specific models, hardware, and inference engine.
GitHub Repo
The new release adds Parity-aware BPE, enabling tokenizers to prioritize improving the language with the worst compression at each merge instead of merely pursuing the highest overall frequency. The feature can be used to train new vocabularies, but it does not automatically reduce Chinese token costs in existing models.
最新模型
GWM Worlds 2 combines autoregressive diffusion, a causal video decoder, and the structured WorldPrompt format to enable real-time control of persistent worlds through text-based actions and camera signals. The system remains a closed research preview, with fast camera movement, long-term consistency, and reproducible evaluation among its clear shortcomings.
AI 安全
Researchers collected 7,534 citations across 760 Sonar queries, finding that long-tail websites frequently appeared in the retrieval evidence used by recommendation systems. Three sites suspected of sharing the same operator accounted for just 2.4% of all citations, and the study did not establish that these pages actually changed the recommendations.
代理工具
New research turns source code, documentation, and tests into operational knowledge that can be loaded on demand, delivering gains across four research benchmarks with the same underlying model and agent framework. Skill-building costs are accounted for separately, however, and the results remain the authors’ own evaluation, so they should not be treated as evidence that skills can replace model training at low cost.
代理工具
The Claude Platform CLI adds `ant apply`, which synchronizes managed agent resources from Markdown, YAML, or JSON files in a repository. It provides previews, dependency ordering, and drift detection, but its state file still contains organization identifiers, and it currently manages only the Anthropic platform.
AI 安全
The open-source AI penetration testing tool Shannon 3.0 adds multi-stage code analysis, candidate vulnerability reconciliation, and native SARIF support. The new version triggers pipeline gates only for successfully reproduced vulnerabilities, but it can modify the target’s state, and 2.x workspaces cannot be resumed.
代理工具
Cohere Labs has released the Agentic Task Ecosystem, which aggregates 696,291 tools from seven directories and maps them to tasks in the U.S. O*NET database. The results suggest that many MCP tools cover only fragments of a workflow, but the 2.6% figure comes from semantic matching and model-based classification—not real-world execution tests.