[hmaxwell]

I just tested both codex 5.3 and opus 4.6 and both returned pretty good output, but opus 4.6's limits are way too strict. I am probably going to cancel my Claude subscription for that reason:

What do you want to do?

  1. Stop and wait for limit to reset
   2. Switch to extra usage
   3. Upgrade your plan

 Enter to confirm · Esc to cancel

How come they don't have "Cancel your subscription and uninstall Claude Code"? Codex lasts for way longer without shaking me down for more money off the base $xx/month subscription.

[ArchieScrivener]

How else are they going to supplement their own development expenses? The more Claude Anthropic needs the less Claude the customer will get. By their own admission that is how the Anthropic model works. Their end value is in using vibe coders and engineers alike to create a persistent synthetic developer that replaces their own employees and most of their customers.

Scalable Intelligence is just a wrapper for centralized power. All Ai companies are headed that way.

[anshumankmr]

IF it helps, try hedging b/w Copilot, Claude, OpenCode and ChatGPT. That is how I have been managing off late. Claude for planning and some nasty things. ChatGPT for quick questions. OpenCode with Sonnet4.5 on Bedrock and Copilot with Sonnet4.5/Opus4.5 (LOL)

[seunosewa]

They introduced the low limit warning for Opus on claude.ai