💻 Technology May 11, 2026

Microsoft researchers find AI models and agents can't handle long-running tasks

The Register
Biting commentary and tech news from the UK
View Channel →
Microsoft researchers find AI models and agents can't handle long-running tasks
Source ↗ 👁 2 💬 0
Companies exploring automated workflows would be well advised to keep their AI agents on a short leash. Microsoft researchers have found that even the priciest frontier models introduce errors in long workflows, the very thing for which AI software has been pitched. Anthropic, for example, says, "Claude Cowork handles tasks autonomously. Give it a goal and Claude works on your computer, local files, and applications to return a finished deliverable." Redmond promotes similar usage, touting Micro

Comments (0)

Sign in to join the discussion

More Like This

Siri AI is coming to newer Apple devices only, here’s the full list
9to5Mac · 22h ago
WWDC, Siri AI, and all of Apple's platforms, on the AppleInsider Podcast
AppleInsider News · 22h ago
Crusoe claimed it “paused” a plan to build a Wyoming data center after it failed to win customers including Google
Latest from TechRadar · 22h ago
Amazon has quietly discounted a whole cauldron-full of Harry Potter Lego kits ahead of Prime Day — here are 12 magical sets to snap up now
Latest from TechRadar · 22h ago
📰
Sam Bankman-Fried loses his bid to overturn his fraud conviction and 25-year prison sentence over the collapse of FTX (Luc Cohen/Reuters)
Techmeme · 22h ago
PureVPN has turned ChatGPT into a VPN assistant that handles the tedious manual tasks for you
Latest from TechRadar · 23h ago