< prev 2 / 12 more >

• 2GPT-5.5-Pro did worse in BullshitBench (twitter.com)
  by amrrs22 minutes ago | 0 comments
• 1Agent regression testing: cutting detection from days to minutes (polarity.so)
  by mihaipo23 minutes ago | 1 comments
• 2Show HN: Video Messaging for Work (flowylabs.ai)
  by talksik32 minutes ago | 1 comments
• 2Everyone in the world has to take a private vote by pressing red or blue (twitter.com)
  by theharrychen33 minutes ago | 0 comments
• 3Show HN: Kloak, A secret manager that keeps K8s workload away from secrets (getkloak.io)
  by neo200633 minutes ago | 2 comments
• 1Hermes.md in Git commit messages causes requests to route to extra usage billing (github.com)
  by adunk44 minutes ago | 0 comments
• 1Show HN: Bulk URL Checker – check 75k URLs from any LLM via MCP (bulkurlchecker.com)
  by carlosofscience44 minutes ago | 1 comments
• 2The Lunar Gateway's primary modules are corroded (arstechnica.com)
  by simonebrunozzi44 minutes ago | 0 comments
• 1Greenfield and Iterative deployment – By superpowers creator (primeradiant.com)
  by sorcercode46 minutes ago | 0 comments
• 2Show HN: I benchmarked how good LLMs are at proofreading English (github.com)
  by artursapek49 minutes ago | 1 comments

< prev 2 / 12 more >