Taelin

@@VictorTaelin

2d

Asked Sonnet-4.5 to perform a refactor. Left it working alone. 5 minutes later, it declared victory. I committed it and started testing. Something was wrong. Many tests broke. I pointed out the issue, and asked it to investigate. It worked for more 3 minutes, found and fixed a

David Ondrej

@@DavidOndrej1

1d

gpt-5-codex-high for Planning. claude-sonnet-4.5 for Execution. trust me.

Alex Albert

@@alexalbert__

1d

The response to Sonnet 4.5 has been incredible. We've also seen some people hitting weekly limits, particularly if you're using Opus. We've just reset limits for all paid users to give everyone a fresh start with Sonnet 4.5.

Ian Nuttall

@@iannuttall

1d

Updated TLDR (after hammering Sonnet 4.5 for 24h); GPT-5-Codex is good and fast Sonnet 4.5 is great and fast GPT-5-High is great and slow Opus 4.1 is no longer needed

eric zakariasson

@@ericzakariasson

1d

here are the models i'm using currently: sonnet 4.5 as daily driver. fast, smart and just gets you gpt-5 codex for the hardest tasks. still most intelligent and finds things no other model does. feel like gpt-5 is the new o3, and sonnet 4.5 is the new sonnet 4 (duh)

Ian Nuttall

@@iannuttall

2d

TLDR; Sonnet 4.5 is good and fast GPT-5 is better and slow Opus 4.1 is best and expensive