Archive
1537 technical news articles
代理工具
SWE-Bench ProMax selected 170 multi-file refactoring tasks from 29,782 candidate commits, with experts rewriting the requirements and reviewing the tests. GPT‑5.2 paired with OpenHands achieved the highest solve rate, but its trajectories show that agents often fail to update related call sites, configuration, and test files.
推論系統
Rather than merely comparing aggregate long-context scores, KVDiagnosis creates a paired FullCache baseline for every compression configuration to track evidence retention, attention, and probability drift. An implementation audit also led the team to exclude 7,800 PyramidKV records with identical results, highlighting how adapter errors can contaminate cross-method evaluations.
AI 安全
SHE decomposes an agent safety harness into a system prompt, rule library, safety memory, and tool policy, then locally revises them based on failure traces. On Agent-SafetyBench, it reduces both attack success and false refusal rates, though real-world deployments must still guard against evaluator bias and unchecked rule growth.
AI 安全
Anthropic says Claude models released starting August 2 will embed invisible markers in text and add signed provenance data to supported images and documents. Technical specifications and third-party detection tools have not yet been released, so the markers cannot currently be treated as definitive proof of AI generation.
最新模型
New research suggests that diffusion LLMs converted from autoregressive models may also inherit safety mechanisms concentrated in a small number of neurons. The researchers also used an open diffusion model to generate adversarial prompts offline, but the promised full code has not yet been released.
開發者平台
OpenAI discontinued `gpt-5.2-chat-latest` in the API on August 10 and officially recommends migrating to GPT‑5.5. The retirement targets an alias that tracks ChatGPT behavior, so engineering teams must still revalidate prompts, tool calls, and output formats rather than treating the migration as an equivalent routing switch.
推論系統
A publicly available, reproducible community vLLM recipe deploys Laguna S 2.1 INT4 on four 24GB RTX 3090 GPUs and handles a real 190K-token request using a precision-matched DFlash draft model. The reported 282.5 tokens/s is a peak under a specific configuration, not sustained throughput, while the quality and compatibility of low-bit quantization remain highly dependent on the checkpoint and inference engine.
PTQ4SNN 把脈衝神經網路長期保留的浮點膜電位納入後訓練量化，按通道配置 2、4 或 8 位元。論文在分類與語意分割上接近浮點模型，但硬體收益仍來自分析模型，且專用程式尚未公開。
代理工具
SkillProx does not retain model-proposed skill modifications outright. Instead, it reruns tasks, rolls back regressive versions, and removes knowledge units with negative utility. All three Qwen models improved on table tasks, but the authors have so far published only a skeletal repository with two commits.
RAG／文件理解
DocMemo does not treat the top-k pages from the initial retrieval as final. Instead, it feeds reasoning feedback back into the page-relevance distribution and resamples. Its three-layer memory improves long-document question answering, but evaluation relies on GPT-4.1, and the public repository remains quite minimal.
推論系統
CoBa initially generates a small number of candidate answers, then uses disagreement and verification scores to decide whether to sample additional candidates or activate a stronger verifier. It achieved 85.13% macro-average accuracy across five reasoning benchmarks, although the results came from offline replay of pre-generated candidate pools rather than testing in a live service.
AI 安全
OpenAI has placed GPT‑5.6‑Cyber, a model designed specifically to reduce refusal rates in offensive security research, in the approval-gated Daybreak Red program rather than the general API. The company rates its cyber capabilities as High but not Critical, while the full system card has yet to be released.