News
AI, cybersecurity, machine learning, scraping & programming news.
Show HN: Swobu – Local LLM Switchboard You Can Share over HTTPS
Managing API keys, rate limits, and provider-specific configurations across multiple AI coding tools is a daily friction for development teams. Swobu, an open-source LLM switchboard released on GitHub, takes a different approach:...
Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain
A travel planning app called Petrel launched this week with a pitch aimed at a common frustration: managing trip confirmations scattered across emails, screenshots, and PDF files. The app reads booking confirmations in any format,...
Insight Partners’ Deven Parekh on why the firm is diversifying while everyone else bets the farm on OpenAI and Anthropic
Deven Parekh, who has co-led Insight Partners for 26 years, sat down with TechCrunch at its StrictlyVC event in New York on Thursday night and laid out why the firm is sticking with a diversified investment strategy while competit...
Show HN: ClientCoded – QA Platform for AI Agents
ClientCoded Ships 40 Pre-Built Test Environments for AI Data Agents Testing whether an AI agent returns correct answers against a real database is hard. You need data, you need to know what the right answer is, and you need querie...
A computational constitution to stop LLM agents from bricking servers
Zero-Trust LLM Forces AI Agents to Ask Before Acting AI agents that write code and deploy applications in seconds are impressive in demos. In production, that same speed becomes a liability. An agent tuned to be helpful and agreea...
Show HN: VibeWorld – a shared terminal world for developers and scientists
VibeWorld Puts a Persistent Cyberpunk World in Your Terminal Discord became a list of servers. Slack became work. Twitter became a feed. VibeWorld is an attempt to build a place instead. It is a persistent multiplayer world that r...
Trump and Mike Johnson think the AI industry is overreacting
Trump and Johnson Push Back on AI Industry Calls to Slow Down A rare moment of agreement among AI leaders has drawn a sharp rebuke from the White House and House Speaker. Anthropic CEO Dario Amodei published an open letter arguing...
Codename MDASH brings agentic AI security scanning to US Government
Microsoft has quietly deployed one of its most ambitious security tools to Azure Government, and it changes the math on how government agencies can protect software that matters. Codename MDASH, a multi-model agentic code scanning...
Ask HN: Career paths to consider if I am better at supporting than creating?
A software engineer's candid post on Hacker News is resonating with developers who find themselves drawn to maintenance and support rather than greenfield building. The anonymous poster, who holds a BS/MS in computer science and h...
Security through obscurity is dead, and AI delivered the fatal blow
Security through obscurity, the long-discredited practice of relying on hidden implementation details to protect systems, has finally run out of places to hide. AI agents are now routinely finding vulnerabilities that defenders th...