Just sent a 5 word message to Claude and my 5-hour limit is already exhausted. After they gave 2x for some days, now it’s over and the free plan is simply unusable. Starting to feel like @AnthropicAI is just pushing everyone toward paid plans.
So it's time for an update! For March 2026... which agentic code product do you currently prefer, Codex (w/ GPT-5.4 xhigh) or Claude Code (w/ Claude Opus 4.6)?
Claude Code has been struggling all day.
So I switched to Codex with GPT 5.4 xHigh.
Honestly? I'm impressed.
Claude Code with Opus 4.6 is still my daily driver when it's running.
But these outages keep pushing me into Codex and Codex keeps delivering.
OpenAI has a real product here.
Anthropic needs to fix the reliability.
Hello. We have reset Codex usage limits across all plans to let everyone experiment with the magnificent plugins we just launched, and because it had been a while!
You can just build unlimited things with Codex. Have fun!
Anthropic just wiped $30 BILLION off IBM’s market cap in one day. 🤯
Claude can now autonomously understand and patch COBOL the legacy code running 95% of ATMs globally.
Legacy migration used to take decades. AI agents are doing it in minutes. The disruption is ruthless.
In 16 months, Claude's computer use went from 14.9% to 72.5%.
That's not a software update. That's a different category of tool entirely.
The thing people called "too unreliable to use" is now the best in the world at it.