Same. I’ve lived in Claude Code since the beta release and last couple of weeks was horrible. I’ve been using codex for last couple of days and it’s much smarter than 4.6.

It worked. Although I have a Claude Code subscription, I got the ChatGPT Pro plan, and 5.4 xHigh at 1.5x speed was better than 4.6 with adaptive thinking disabled. I was working all day, about 8 hours, and did not run into any limits. 5.4 surprised me many times by doing things I usually would not do myself, because I am lazy, so yeah, I am sticking with 5.4 for now until all the Claude drama is over.

Absolutely right! You must be fun at parties .

This has been my experience too.

Have any of you heard of map reduce

Looks good. I’ll give it a try.

Or CLI.

I used Claude in chrome and Claude Code. It did everything for me.

Anyone who has all three and found iPad still useful? I’m mostly on my MacBook and use iPhone when I’m not on my MacBook, or Apple TV.

Agreed. I removed it.

So the only difference between slash custom command and agent skills is that they can be invoked only when needed instead of stuffing the whole markdown file? I’m trying to understand how is this different from what we already have in markdown files.

Correct. It helps by not distracting your LLM with a prompt that is, in X% of the cases, irrelevant to the task at hand.

However, when you DO need to do something special (like create a new endpoint), the LLM knows where to get more info on this.

Kinda like a library of „how to“ books.