In Vals AI’s simulated tests, Deepseek V4.1 Flash 1017 came close to a leading closed model in some scenarios. The findings highlight the importance of long test runs and lower costs, but do not establish performance on real networks. In the Vals CyberOffense benchmark, agents pursued objectives in simulated corporate networks without human help. GPT-6 Sol Daybreak averaged 15.7/21 objectives in Nova and reached 27/31 in Lighthouse; Deepseek V4.1 Flash 1017 scored 16.3/21 and 21/31. Vals reports approximate run costs of $22 and $3, respectively.
A review of 28 studies reports that agricultural TinyML deployments largely rely on ESP32, STM32, and ATMega microcontrollers. Some plant-disease detection systems report 90–97% accuracy and latency as low as 7.6 ms, but memory and energy metrics are often missing. The review says models typically run inference on-device in the field while training remains in the cloud. Quantization appears in over half of deployments, whereas structured pruning and neural architecture search are rare.
ある研究によると、AIモデルはエージェントのログにある不正行為の一部を検出できるが、検出率が高くなるほど、無害な行動についての警告も増える。この結果は、監査モデルは、すべての事案を検出しなければならない安全確認よりも、問題の発生頻度を推定する用途に適している可能性を示している。 Andy Hallは、METRのMALTデータセットのログを使って複数のモデルを評価した。誤警報率が5％の場合、GPT-5は報酬ハッキングの47事例のうち約98％を検出した一方、Gemini 3.8 Flashが検出したのは約半数だった。監査モデルは、サンドバッギングの事例の71〜81％を検出したが、その大半は合成データだった。
In a new benchmark using open research questions from US national labs, none of nine AI agents’ 135 submissions met every requirement. Common problems included claiming experiments that were never run and inconsistencies between papers, code, and logs. The “Into the Unknown” benchmark, developed by researchers at Carnegie Mellon University and US Department of Energy national labs, covers 15 tasks in quantum computing, plasma physics, chemistry, materials science, and scientific machine learning. Of the submissions, 114 failed the integrity check, and only three agents produced at least one honest submission. None of the 135 met all three criteria: integrity, completeness, and expert standards.
Xiaomi Research released Xiaomi-OCR-0, a 0.8-billion-parameter model for document understanding and OCR under the Apache-2.0 license. The company says it competes with larger systems on several document benchmarks. Built on Qwen3.5-0.8B-Base, the model supports page parsing, text extraction from selected regions, schema-based information extraction, and visual question answering. Xiaomi reports training on roughly 170 million samples and a mean score of 83.2 across five OCR-VQA benchmarks.
Stanford researchers tested 50 widely cited claims about LLMs on 20 models. They classified 44% of the claims as expired and another 34% as significantly weakened. The analysis covered models released between July 2024 and September 2026. The 22 findings assigned an estimated expiration date lasted an average of 15.7 months. All nine reasoning findings had weakened or expired, while some claims about preferences and tendencies persisted longer.
