699 results on this page · clear filters

ai Oct 20 Benchmarking Bot Detection Systems Against Modern AI Agents in 2026 Bot detection benchmark 2026: rates from 9% to 99% across AI agents and stealth browsers A bot detection benchmark was revisited in 2026 with stealth browsers and modern AI agents, finding detection rates ranging from 9% to 99%. A... ai Oct 20 Show HN: Contrack – Self-hosted contact manager and people search Contrack puts self-hosted contact management within reach Contacts accumulate across dozens of applications. Social networks, professional platforms, and personal databases each hold fragments of the same relationships. When every... ai Oct 20 Desktop control for AI agents without screenshot dependence clawdcursor shifts AI desktop automation from pixel guessing to structured element interaction. The tool reads the operating system accessibility tree first, fuses it with OCR only when needed, and routes every action through a si... ai Oct 20 LLM-d 1.0, an open source stack for distributed inference llm-d 1.0 shipped at the PyTorch Conference as an open-source Kubernetes-native stack for distributed LLM inference. Google co-founded the project with Red Hat and IBM, drawing more than 500 contributors across 25 organizations in... ai Oct 20 DataChat – Free, zero-dependency Java tool ask questions with Claude/Offline AI DataChat lets analysts ask CSV questions in plain English and get an answer plus a chart. The single-file Java Swing desktop app requires no external dependencies. It works with Claude from Anthropic for natural-language understan... ai Oct 20 Presentation: Beyond the Prototype: Scaling Framework Agnostic AI Agent Infrastructure with Ray Deepak Mohanakumar Chandramouli and Bhumik Vinodkumar Thakkar presented a session on building agents and running them at scale with Ray. Ray is an open-source distributed computing framework that specializes in machine learning wo... ai Oct 20 Ask HN: How to get the most intelligence out of your agents? When LLMs outpace agent tooling The Ask HN thread "How to get the most intelligence out of your agents?" struck a nerve among developers who have noticed a consistent pattern: ChatGPT often feels "smarter" than coded agents, even... ai Oct 20 Refuseless: Open and Abliterated LLMs Refuseless: hosted API for abliterated GLM models A new hosted inference API called Refuseless puts abliterated open-weight models within reach of any application that can speak the OpenAI SDK format. The service runs Z AI's GLM-5... ai Oct 20 OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory Multimodal large models have advanced considerably on visual reasoning tasks, yet a significant gap remains when tasks require evidence beyond internal model knowledge. A controlled evaluation across 22 benchmarks confirms that me... ai Oct 19 Nscale and Anthropic are reportedly in talks for yet another $45 billion compute deal The AI infrastructure market continues to see massive capital deployment. Anthropic and Nscale announced a $45 billion compute deal less than a month ago, and Bloomberg reports the two companies may announce another $45 billion ag...