← Back to context Comment by sunaookami 4 days ago This sounds more like DeepSeek ;) 5 comments sunaookami Reply flexagoon 4 days ago Closed models just don't show this thinking process directly to the user 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. 1 reply → icepush 4 days ago From a recent DeepSeek session:"Wait, what am I? I am claude, or something similar"
flexagoon 4 days ago Closed models just don't show this thinking process directly to the user 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. 1 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. 1 reply →
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. 1 reply →
icepush 4 days ago From a recent DeepSeek session:"Wait, what am I? I am claude, or something similar"
Closed models just don't show this thinking process directly to the user
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.
1 reply →
From a recent DeepSeek session:
"Wait, what am I? I am claude, or something similar"