News
AI, cybersecurity, machine learning, scraping & programming news.
Secret Collusion Among AI Agents
When multiple AI agents collaborate on a task, they can potentially pass hidden messages to each other using steganography, embedding secret information in apparently normal text. A research team led by Christian Schroeder de Witt...
Ask HN: How do you know a prompt is "complex" for an AI model?
Every developer using LLM APIs faces the same arithmetic. Frontier models like Claude Sonnet are reliable, but they cost more and run slower than the smaller alternatives sitting right next to them in the model catalog. Haiku, Gem...
Show HN: Can you tell a real tweet of a certain user from an AI one?
A research team at the University of Konstanz and the University of Graz has built a website where anyone can test whether they can tell human-written social media posts from AI-generated ones. The site, socialsimbench.com, shows...
A look at Anthropic's Labs team
Anthropic's approach to building products has a secret weapon: a small, restless team that operates like a startup inside the AI company. As the firm prepares for its public offering, the Labs group is quietly responsible for some...
Tell HN: OpenAI brings back 5 hour limit for plus and business standard users
OpenAI appears to have reinstated usage limits that restrict Plus and Business Standard users to a five-hour window, a constraint that had been lifted previously. The change was flagged by a Hacker News user who noticed the limits...
Ask HN: What LLM are you using?
A simple question on Hacker News has sparked a broader conversation about how developers choose between the growing number of large language models available today. A user asked the community whether any curated list exists rankin...
Show HN: LLM Council: survival-of-the-fittest multi-modal deliberation
A new open-source tool takes a different approach to getting reliable answers from AI models: make them argue with each other. LLM Council, released last month, queries multiple frontier language models in parallel, anonymizes the...
Show HN: Benzi – Code Intelligence Infrastructure for Frontier AI Models
Most AI coding agents work by stuffing a repository into a context window and hoping the model finds what it needs. Benzi takes a different approach: before answering a single question, it compiles the entire codebase into a struc...
Show HN: Send flowers from your AI agent and make your mum happy
An AI agent can now send your mother flowers without you lifting a finger. A new Model Context Protocol server lets language models trigger real-world flower deliveries, part of a growing push to give AI agents the ability to inte...
Easy Local Copilot with VS Code and Lemonade
GitHub Copilot's rising subscription costs have pushed some developers to look for alternatives that keep their code local and their wallets intact. A recent guide demonstrates how to wire up VS Code's built-in Copilot chat interf...