Archive
1527 technical news articles
最新模型
The new method uses a large teacher model to synthesize task data, then trains a function-specific LoRA for each task so subsequent requests do not need to call a remote model. It achieves 83.6% semantic accuracy on a difficult benchmark, but compilation still requires a teacher API, about 40 GB of accelerator memory, and output validation.
AI 安全
CVE-2026-59822 allowed forged Bearer tokens to bypass LiteLLM authentication in a specific OAuth2 passthrough path, enabling attackers to list and invoke configured MCP tools. The vulnerability was fixed in version 1.84.0, but its addition to CISA’s KEV catalog makes inventorying public endpoints and rotating upstream credentials an immediate priority.
代理工具
The Copilot CLI research preview no longer selects just one model for each task. Instead, it routes tasks among three workflows: direct execution, staged escalation, and cross-model review. GitHub’s offline tests indicate that some workloads may reduce estimated costs, but the router, quality gates, and internal benchmark have not been disclosed.
代理工具
Researchers from Tencent Hunyuan and collaborators make terminal environments progressively harder across generations based on scenario novelty, skill rarity, and execution length, without continually using rollouts from the model being trained to identify weaknesses. In a 200-step reinforcement learning experiment, the method outperformed co-evolution baselines, but the findings currently come only from the authors, and a complete reproduction package has not yet been released.
AI 安全
The AAIF open-source agent Goose 1.49 allows `PreToolUse` policies to reject tool calls when execution fails, preventing operations from continuing after security checks break down. The new release also adds a stable `tool_call_id` and result events, but remains fail-open by default, requiring administrators to explicitly change the configuration.
最新模型
Google has moved Gemini 3.8 Flash into production, offering a 1 million-token context window, three thinking levels, and built-in tools, while making it the default model for Antigravity managed agents. Coding benchmark results have improved, but most figures still come from Google, and the model card also reveals a relative decline in non-English safety evaluations.
AI 安全
Cloudflare’s early-preview service combines source code analysis results with actual routes, traffic, WAF status, and attack events, then uses GPT-5.6 Cyber to validate vulnerabilities and proposed fixes. The model does not directly modify the environment, but data is sent to OpenAI for inference, and Cloudflare has not disclosed false-positive or remediation success rates.
AI 基礎設施
HyperPod InstantStart orchestrates EKS, GPU capacity, training, inference, and storage operations as retryable, stateful workflows, then exposes them to agents through MCP tools. Agents do not operate the AWS CLI directly, but deployers remain responsible for IAM, Kubernetes, networking, and cross-service cost management.
電腦視覺
Scal3R retains a frozen CUT3R or STream3R backbone, using lightweight query tokens to estimate relative poses against multiple historical keyframes before passing them to online pose graph optimization. The authors report a mean ATE on KITTI more than 60% lower than the strongest online competitor, but the results use Sim(3) alignment and therefore should not be interpreted as preserving true scale.
最新模型
Microsoft Research’s streaming speech model interleaves audio chunks, brief lookahead, and the existing transcript to directly output “who said what.” The public release supports ten languages and custom hotwords, but expected speaker-attribution latency remains two seconds, and performance degrades during prolonged overlapping speech.
推論系統
KAIST and Google DeepMind have introduced Declarative Attention, which allows existing models to switch among global, focused, and local attention modes within their reasoning text. The authors reduced attended tokens by 31.1% to 52.0% across two models, though the speed gains remain model-based estimates and accuracy declined slightly.
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.