IMO for coding you want ad much intelligence as possible to ship better code with fewer bugs. ds4 is great engineering tho.
@steipete
-
Comparing token count to coding, can use Sonnet-class model
By
–
compared to coding these are very few tokens, and you can even use a Sonnet-class model (= gpt 5 mini)
-
It runs on Codex, Copilot, or their own harness
By
–
it runs on codex now. or copilot. or our own harness!
-
User questions if ‘load-bearing’ is unique to Claude, not Codex
By
–
is load-bearing a Claude thing? Haven’t seen that on Codex. Maybe I don’t have enough load
-
Running prompts from a project folder containing all projects
By
–
I run most prompts of a project folder all my projects are in, works fine?
-
Prompting ‘do whatever you need to do’ yields exactly that
By
–
If you prompt "do whatever you need to do" you'll get exactly that.
-
Subscription cost comparison: Chinese labs cheaper but older quality
By
–
The 100/200$/month sub works well for most. There’s also really competitive offering from chinese labs out, quality is usually a year behind latest gen but for 10% of the costs.
-
Cloud agents eliminate need for open MacBooks
By
–
Fewer people having to run around with their MacBooks open as it makes running agents in the cloud easy.
-
Terminal command executing codex with GPT-5.5-cyber
By
–
codex -C ~/projects/openclaw -m gpt-5.5-cyber time pic.twitter.com/6ANgzM1JKJ
— Peter Steinberger 🦞 (@steipete) 12 juin 2026codex -C ~/projects/openclaw -m gpt-5.5-cyber time
-
Model improvements in diffs: structure, less repetition, file splitting.
By
–
you look at the diffs and see that the model improved structure, reduced repetition, broke apart large files etc.