News for hackers. Stuff that matters.
Re:System Card: Claude Mythos Preview [pdf] by jeswin on Tuesday April 07, 2026 @08:16PM (#47683032)
It really is, for complex tasks. Claude excels at low-mid complexity (CRUD apps, most business apps). For anything somewhat out of the distribution, codex at the moment has no peer.
Re:System Card: Claude Mythos Preview [pdf] by ttul on Tuesday April 07, 2026 @11:52PM (#47684963)
I find that more experienced devs are more likely to prefer Codex… anecdotal but… it’s a thing.
Re:System Card: Claude Mythos Preview [pdf] by xvector on Wednesday April 08, 2026 @12:26AM (#47685227)
This is because no one bothers to set thinking to high, as it now defaults to medium in CC.

Once you set thinking to high it works just as well as 5.4 even for pretty complex tasks

Re:System Card: Claude Mythos Preview [pdf] by jeswin on Wednesday April 08, 2026 @01:20AM (#47685624)
I have always used Claude at max thinking levels since it launched. It has never been up to the task. For clarity, the task being this: https://github.com/tsoniclang/tsonic

Meanwhile, there are half a dozen other projects (business apps, web apps etc) where it works well.