← Back to context Comment by flexagoon 4 days ago Closed models just don't show this thinking process directly to the user 3 comments flexagoon Reply mcapodici 4 days ago Depends on harness. flexagoon 3 days ago No, I mean they don't show it at all in their API to prevent distillation. The reasoning is encrypted and only accessible by their server. They sometimes show a summary of the reasoning, but it's not the same as the actual contents of the reasoning. mcapodici 2 days ago Thanks I didn't know that.
mcapodici 4 days ago Depends on harness. flexagoon 3 days ago No, I mean they don't show it at all in their API to prevent distillation. The reasoning is encrypted and only accessible by their server. They sometimes show a summary of the reasoning, but it's not the same as the actual contents of the reasoning. mcapodici 2 days ago Thanks I didn't know that.
flexagoon 3 days ago No, I mean they don't show it at all in their API to prevent distillation. The reasoning is encrypted and only accessible by their server. They sometimes show a summary of the reasoning, but it's not the same as the actual contents of the reasoning. mcapodici 2 days ago Thanks I didn't know that.
Depends on harness.
No, I mean they don't show it at all in their API to prevent distillation. The reasoning is encrypted and only accessible by their server. They sometimes show a summary of the reasoning, but it's not the same as the actual contents of the reasoning.
Thanks I didn't know that.