Re:Planning > Agents: Getting Reliable Code from LLMs
by zakelfassi on Tuesday November 04, 2025 @09:05PM
(#45818192)
Everyone's chasing bigger context windows, but more tokens don't necessarily mean more intelligence. Once an agent fills its window with noise, reasoning quality drops fast. This piece breaks down why "convenience workflows" degrade model IQ and why architectural planning still beats automation.
[ Parent
| on HN ]
There are no comments on this comment yet.