I really don't get the deepSeek love. I haven't tried the full model, but the 70B parameter distill is trash. It isn't actually a reasoning model. It merely apes being a reasoning model. It is really good at sounding like it is reasoning but it hallucinates far more than the llama3.3 model on which it is based.
I suspect the full model has similar features. It is reassuring to users to see that it is attempting a rationalization but the actual output isn't that great.
Daniel Wigton
npub1w4…q30zp
2025-02-12 23:40:54
Author Public Key
npub1w4jkwspqn9svwnlrw0nfg0u2yx4cj6yfmp53ya4xp7r24k7gly4qaq30zpPublished at
2025-02-12 23:40:54Event JSON
{
"id": "5ea2072c861a49fe3c20d9f29e234e57063f5a42ffba59c427228c3ee3d3429b",
"pubkey": "75656740209960c74fe373e6943f8a21ab896889d8691276a60f86aadbc8f92a",
"created_at": 1739403654,
"kind": 1,
"tags": [],
"content": "I really don't get the deepSeek love. I haven't tried the full model, but the 70B parameter distill is trash. It isn't actually a reasoning model. It merely apes being a reasoning model. It is really good at sounding like it is reasoning but it hallucinates far more than the llama3.3 model on which it is based.\n\nI suspect the full model has similar features. It is reassuring to users to see that it is attempting a rationalization but the actual output isn't that great.",
"sig": "b4c284176466bd80324761d1145ec39200d4f26d384077b61dcc0c6984f283d239ca4cee1c5d041340c293c9ddf88de4414be9a3dc9a67cb5b6a81d7156ecb6e"
}