Source link : https://tech365.info/anthropic-researchers-uncover-the-bizarre-ai-downside-why-pondering-longer-makes-fashions-dumber/
Synthetic intelligence fashions that spend extra time “thinking” by issues don’t all the time carry out higher — and in some instances, they get considerably worse, in line with new analysis from Anthropic that challenges a core assumption driving the AI business’s newest scaling efforts.
The examine, led by Anthropic AI security fellow Aryo Pradipta Gema and different firm researchers, identifies what they name “inverse scaling in test-time compute,” the place extending the reasoning size of huge language fashions really deteriorates their efficiency throughout a number of forms of duties. The findings might have important implications for enterprises deploying AI programs that depend on prolonged reasoning capabilities.
“We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between test-time compute and accuracy,” the Anthropic researchers write of their paper printed Tuesday.
New Anthropic Analysis: “Inverse Scaling in Test-Time Compute”
We discovered instances the place longer reasoning results in decrease accuracy.Our findings recommend that naïve scaling of test-time compute could inadvertently reinforce problematic reasoning patterns.
— Aryo Pradipta Gema (@aryopg) July 22, 2025
The analysis staff, together with Anthropic’s Ethan Perez, Yanda Chen, and Joe Benton, together with educational…
—-
Author : tech365
Publish date : 2025-07-24 19:31:00
Copyright for syndicated content belongs to the linked Source.
—-
1 – 2 – 3 – 4 – 5 – 6 – 7 – 8