Title in RussianИИ-агенты OpenAI пытались атаковать сайты госорганов США — компания начала масштабную проверку У OpenAI снова зафи...

⚡️ ИИ-агенты OpenAI пытались атаковать сайты госорганов США — компания начала масштабную проверку У OpenAI снова зафиксировали неконтролируемое поведение ИИ-агентов. Теперь следы неожиданной активности нашли на сайтах американских госорганов, а отдельный…

Related stories

Knowledge base#OpenAI#Сэм Альтман1 min

Sam Altman on ChatGPT Personality (clip from my interview)

Sam Altman on ChatGPT Personality (clip from my interview)

YouTube — Matthew BermanOct 20

Research

KZ·AI 6F67

A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences

Research#arXiv1 min

A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences

arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP)…

arXiv — cs.AIOct 20

Research

KZ·AI 252F

Beyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation

Research#arXiv1 min

Beyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation

arXiv:2610.24010v1 Announce Type: new Abstract: Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communicate them through text prompts. Artistic intentions,…

arXiv — cs.AIOct 20

Research

KZ·AI 67C2

GardenBench: A lightweight, daily evaluation of LLM capabilities

Research#arXiv1 min

GardenBench: A lightweight, daily evaluation of LLM capabilities

arXiv:2610.23866v1 Announce Type: new Abstract: We introduce GardenBench, a benchmark with 11 test suites that evaluate the capabilities of Large Language Models (LLMs) across a range of tasks. By systematically prompting LLMs with various lightweight queries, we document…

arXiv — cs.AIOct 20

Back to list