AI · អត្ថបទ
AI Coding Agents Ace Lab Tests but Finish Under 10% of Simulated Office Tasks
The Decoder ·

មើលត្រួសៗ
Researchers put AI coding agents to work as digital employees inside a simulated software company, with colleagues, project boards, and chat logs. Even the top models, Claude Opus 5.5 and GPT-6 Astra, fully finished fewer than one in ten tasks.
ចំណុចសំខាន់ៗ
- AI coding agents are getting close to top scores on standard tests.
- In this new experiment, they worked inside a simulated software company for the first time.
- The company had colleagues, project boards, and chat histories.
- Even Claude Opus 5.5 and GPT-6 Astra fully completed fewer than one in ten tasks.
ហេតុអ្វីវាសំខាន់
Strong scores on standard tests do not show that AI can handle real, multi-step work with other people. The gap matters for anyone judging how much work these tools can take on.
ប្រភពដើម
AI coding agents ace isolated tests but complete fewer than one in ten tasks in a simulated workplace
The Decoder · Nov 23, 00:15 KST
Read on The Decoder ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to The Decoder.
បន្ថែមពីវិស័យនេះ
- Senator Kennedy Mocks Jensen Huang Affair as Focus Shifts to Chip Export Loopholes
US Senator John Kennedy joked about former Nvidia CEO Jensen Huang's reported affair with a suspected Chinese spy. His main concern was how China seemed to get around US export controls on advanced AI chips.
The Guardian · Nov 23, 04:34 KST - Cartesia's H-Net Tries a Smarter Way to Split Text for AI Training
Cartesia's H-Net is a new way for AI models to handle text, moving past the traditional tokenization step. Instead of splitting text into fixed chunks, it learns to group raw bytes on its own. The video says this can train models much faster on selected tests and help them handle unfamiliar data better.
bycloud · Nov 23, 04:03 KST - OpenAI Proposes Shared AI Development Limits Tied to Safety Milestones
OpenAI's chief scientist Jakub Pachocki proposed that top AI developers agree on shared limits on frontier AI development, tied to measurable milestones. He warned that if pretraining progress speeds up as early as 2027, alignment and monitoring research may not keep pace. OpenAI also said AI has already helped with some model design work.
Unite.AI · Nov 23, 03:43 KST - Why Data Centers Are at the Center of the Big Tech Backlash
Journalist Paris Marx's new book, Hyperscale, examines how data centers and generative AI have become a political flashpoint. In an interview with TechCrunch, he described data center buildouts as unsustainable and said the opposition is part of a wider backlash against tech companies.
TechCrunch · Nov 23, 03:08 KST