Nostr Web Client

Anyone use the Deepseek R1 model yet? I tried it yesterday and it didn’t seem all that better than existing LLMs. Is that a limitation of the free model?

Logen 11mo ago

It’s not great. I get too many hallucinations with it

Reply to this note

Please Login to reply.

Discussion

Logen 11mo ago

note1wsmtalu5ql7uwu80pu0xzyevx8rc4ssmjg7txvhew6strmah8nkq8fwqzg

Sync 11mo ago

With bitcoin questions I’ve only had decent results with spirit of Satoshi, the training data out there about bitcoin is garbage, but it’s an interesting test case 💪

Avi Burra 11mo ago

Yeah the preface rambling before the real answer is annoying

Logen 11mo ago

I guess it’s called reinforced learning, but it’s more like reinforced confusion

Avi Burra 11mo ago

It’s also passive aggressive sometimes. “The user seems to be under the impression that I somehow have access to this information…” 😂