Archive
1540 technical news articles
AI 科學研究
OpenAI says its unreleased Astra model solved or advanced ten problems in mathematics and theoretical computer science and has released a 249-page manuscript. Each result includes a buildable Lean 4 formal certificate, but the mathematical significance and the manuscript’s arguments still await review by domain experts.
推論系統
Cloudflare uses an FP8 KV cache to expand Kimi K2.6’s concurrency capacity and switches to INT4 weights for GLM 5.2 decoding. The system also adds page-generation tags to the shared KV cache to prevent multi-tenant requests from reading incorrect cached data.
最新模型
MiniMax has released the weights for its H3 video model, enabling developers to run image-to-video generation with synchronized audio locally. ComfyUI has added an official workflow, but consumer GPU tests largely rely on pruned and INT8 derivative files and should not be treated as full-quality reproductions of the original weights.
最新模型
Alibaba is moving Qwen3.8-Max to a production API, targeting software development and long-running knowledge work, while announcing plans to release weights for both the flagship and 27B models. The model ranks near the top of a community coding arena, but complete technical documentation on its architecture, active parameter count, and self-hosting costs remains unavailable.
AI 安全
CAGE does not merely inspect the tool response currently visible to an agent. It verifies that every plausible correct binding permits the same action. The research proves that checking categorical fields and numeric errors separately cannot guarantee safety when both change simultaneously.
代理工具
The compatibility period for `used_copilot_coding_agent` in GitHub Copilot usage reports expired on August 1. Integrations should migrate to `used_copilot_cloud_agent`. The two fields previously returned the same Boolean value, but the legacy field is no longer guaranteed after the deadline, potentially causing enterprise adoption reports to silently undercount usage.
GitHub Repo
NVIDIA, the Linux Foundation, Hugging Face, Microsoft, and other organizations have formed the Open Secure AI Alliance to address vulnerabilities in agents and AI software with open models and tools. Its first concrete contributions include NVIDIA’s NOOA framework, but the alliance has yet to announce common specifications, governance processes, or a delivery timeline.
推論系統
VIDRAFT has published the highest- performing verified configuration from the Fast Gemma Challenge, pushing Gemma 4 E4B to 510.58 tokens/s on a single NVIDIA A10G while holding perplexity at 2.3930. The result comes from stacking multiple inference optimizations, but the test uses a single stream, fixed hardware, and a private prompt set, so it should not be equated directly with production throughput.
硬體
The North American Electric Reliability Corporation requires transmission planning and system operations entities to report by August 3 on seven computational load measures covering models, stability studies, commissioning, and dynamic disturbance recording. This is not a generic energy-policy declaration; it requires the second-scale load shedding and power oscillations of AI data centers to become part of power-grid engineering models.
AI 安全
New research suggests that the JSON-style tool specifications used by agents are not merely neutral interfaces and may suppress models’ internal refusal representations. By separately evaluating safety before execution using flattened text specifications, SafeKeep increased the average refusal rate for harmful requests from 23.8% to 70.6%.
AI 基礎設施
Etched’s first N4P inference chips have entered rack-level validation. The system uses low-voltage compute arrays and cluster-scale memory to address throughput and latency bottlenecks, respectively. The company claims sparse MoE workloads can sustain more than 80% of peak FLOPs, but has yet to publish reproducible model, power, or end-to-end performance data.
代理工具
A Microsoft Research team jointly updates synthetic applications, tasks, and graders based on agent failure trajectories instead of merely adding more static webpages. The 9B model’s average success rate across 14 evaluations rose from 36.5% to 67.1%, although only four environments have been publicly released as benchmarks.