News
AI, cybersecurity, machine learning, scraping & programming news.
Ask HN: Are agent orchestrators an anti-pattern?
A question on Hacker News is pushing at a nerve in the AI agent community: are the orchestration layers that sit between language models and the tools they call actually making things worse, not better? What an agent orchestrator...
Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation
Zhou Yu, co-founder of Arklex AI and a professor at Columbia University, has a blunt assessment of the AI agent landscape: 95 percent of agents remain stuck in demo mode. They are impressive in controlled settings, but they cannot...
10-task GLM 5.3 harness bench: Claude, OpenCode, pi, zcode, Hermes and 3code
A developer running independent benchmarks on AI coding harnesses has published results that show wide disparities in how different tools use tokens to solve the same problems. The test, conducted on GLM 5.3 using ten SWE-bench ve...
Speculative Decoding in vLLM on AMD GPUs
vLLM has added support for speculative decoding on AMD GPUs, a technique that lets the serving system verify multiple drafted tokens in a single pass through the target model. The feature works across five different drafting metho...
Chess5.ai – Play Chess, Go, Xiangqi, Gomoku, and Othello Against LLMs
A new open-source project puts language models to the test across five classic board games, pitting them against humans and each other to measure something that benchmarks cannot capture: how well a model actually plays when it ha...
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites
A new research paper argues that alignment, the project of making AI systems behave according to human values, is currently aimed at the wrong problem. Before asking whether language models share the right values, the paper conten...
Show HN: Crew — Let Claude/Codex/OpenCode agents talk to each other
Running multiple AI coding agents on the same project has always meant choosing between isolation and coordination. Worktrees let each agent operate independently but duplicate the codebase. A single checkout avoids duplication bu...
CERN Renounces RHEL in Favor of Debian for Its Accelerator Controls Infrastructure
CERN is moving its accelerator-control fleet from Red Hat-derived Linux to Debian. The decision, presented by engineers Federico Vaga and Nikos Tsipinakis at MiniDebConf Winterthur, marks a sharp break from two decades of building...
vlt 1.0 Ships as a Drop-in npm Replacement with Phased Installs, Graph Queries, and Malware-Blocking
vlt 1.0 shipped this week as a drop-in replacement for npm, and it arrives at a moment when the JavaScript ecosystem is actively rethinking how package managers handle untrusted code. Built by the original creators of npm, vlt spl...
What animal has a prime number of legs? And why does this confuse LLMs?
A simple question, "What animal has a prime number of legs?", has exposed a consistent failure mode across multiple language models: the inability to hold a basic mathematical fact in memory while answering a straightforward factu...