If practitioners focus on running applications on future models (GPT-5, Claude 4, GPT-5, Gemini 2.0) via zero-shot prompting, they may be able to achieve comparable performance on some applications using agentic reasoning on earlier models.
causalpending
Speaker
Andrew NgEvidence Quote
“if you're looking forward to running your thing on gp5 zero shot you know you mayble to get closer to that level performance on some applications than you might think with agenting reasoning um but on an early model”
Created: 8/11/2026, 1:37:51 AM
Your notes
Loading notes...