A realistic comparison of Opus and Codex
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
Claude Code vs Codex vs Cursor (an honest comparison)
Theo - t3․gg
17.9k views
Realistic advice about software dev right now
Theo - t3․gg
172.0k views
This model is kind of a disaster.
Theo - t3․gg
166.2k views
Claude Mythos and the end of software
Theo - t3․gg
287.6k views
Cursor, Claude Code and Codex all have a BIG problem
Theo - t3․gg
134.9k views
My new app is really stupid (I wrote none of the code)
Theo - t3․gg
58.4k views
The end of the Clawdbot saga
Theo - t3․gg
107.7k views
Agentic Coding Has A HUGE Problem
Theo - t3․gg
95.7k views
Opus 4.6 Is The Best Coding Model Ever Made*
Theo - t3․gg
106.6k views
I asked Sam Altman about the future of code
Theo - t3․gg
71.2k views
Top Comments (10)
$20 Codex gives you more usage than $100 Claude
Best model counter counter: 9230
I don't think you know what renaissance means theO.
BTW, if you ever run into the claude code "Error: Error during compaction: Error: Conversation too long." you can change model to `/model sonnet[1m]` and then `/compact` and then go back to opus. (or opus[1m] for the compaction if that works for your plan)
My current setup is "claude for planning, codex for real work". Claude tends to be really good when I want to refine a vague idea into an actionable plan, and codex is great when I want to go from an actionable plan to code.
Here we go, here for the fight
Can’t wait for” My Robot is better than your Robot” comments in the future.
It's Claude Code. I don't have most of those issues with Opus 4.6 in other harnesses
22:24 he said it , he said it
"Not missing the details" is such a great way to describe Codex. Totally agree, it's really strongest at considering everything you've said, and not just randomly skimming over provided context and going off and doing it's own thing
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
$20 Codex gives you more usage than $100 Claude
Best model counter counter: 9230
I don't think you know what renaissance means theO.
BTW, if you ever run into the claude code "Error: Error during compaction: Error: Conversation too long." you can change model to `/model sonnet[1m]` and then `/compact` and then go back to opus. (or opus[1m] for the compaction if that works for your plan)
My current setup is "claude for planning, codex for real work". Claude tends to be really good when I want to refine a vague idea into an actionable plan, and codex is great when I want to go from an actionable plan to code.
Here we go, here for the fight
Can’t wait for” My Robot is better than your Robot” comments in the future.
It's Claude Code. I don't have most of those issues with Opus 4.6 in other harnesses
22:24 he said it , he said it
"Not missing the details" is such a great way to describe Codex. Totally agree, it's really strongest at considering everything you've said, and not just randomly skimming over provided context and going off and doing it's own thing