unknown

I know this is pretty well established at this point, but Codex 5.3 is a much more effective model than Opus 4.6. I went back and forth on both for a bit, but haven’t touched Opus at all now for a full week. First model to get me off of Opus… ever. Good job Codex team.

Guillermo Rauch

Vercel's AI support agent now autonomously handles ~90% of customer inquiries without human intervention. Interestingly, upgrading from Claude Opus 4.5 to 4.6 caused measurable performance and sentiment degradation, highlighting that newer models aren't always better for specific use cases. The author expresses bullishness on AI Gateways and open AI SDKs as tools for managing model selection flexibility.

📈 The Vercel support agent is now handling ~90% of customer inquiries without human intervention.

Shockingly, we've been unable to upgrade to Opus 4.6 from 4.5 without measurable performance and customer sentiment degradation.

The "best model" is a moving target. Bullish on AI Gateways and open AI SDKs 😉!

<p>📈 The Vercel support agent is now handling ~90% of customer inquiries without human intervention.

Shockingly, we've been unable to upgrade to Opus 4.6 from 4.5 without measurable performance and customer sentiment degradation.

The &quot;best model&quot; is a moving target. Bullish on AI Gateways and open AI SDKs 😉!</p>