Comment by nojs
1 day ago
Claude code’s plan mode began its slow march towards deprecation when they hid the “clear context and implement” option behind a flag. From the discussion at that time it seemed that the developers considered it mostly a legacy feature, and that newer models are smart enough in long context not to need it.
There's some pretty interesting evidence that this feature actually just increased costs: https://stencil.so/blog/prewalk
Wait, you can turn that back on? Where's the flag?
The flag is:
Boris rationale was "with 1m context window, most users don't need it anymore."
https://x.com/bcherny/status/2035375125382451648
This part I find a little disappointing. The plan is the perfect boundary to cut context which still isn’t free, even if models can handle a lot of it now.
Remember, Anthropic knows best for your workflow!
/s
This is why open harnesses and open models will always be superior, it's only a matter of time until someone decides that something you use isn't worth maintaining anymore. The reply from the Anthropic employee up above doesn't give me much confidence that Claude users will be able to continue using plan mode forever.
Codex and Claude Code are the best harnesses out there by a long shot. They work out of the box, require no real config, and just do the thing.
The flexibility and lightweight nature of open harnesses is mainly useful for open models. These models are considerably far behind the frontier and need a lot more steering. Complex harnesses confuse them. I use open harnesses for my OSS model rig because the model needs it.
> Codex and Claude Code are the best harnesses out there by a long shot. They work out of the box, require no real config, and just do the thing.
Even if I agreed, that doesn't address my point: Claude Code might be the world's best harness right now, but that doesn't stop an Anthropic employee coming along tomorrow and taking a giant steamy dump on the thing you like most about it. You're using their workflow, not your own.
1 reply →