News for hackers. Stuff that matters.

A comment on You can now train a 70B language model at home. Parent comment

Re:You can now train a 70B language model at home by pbhjpbhj on Friday March 08, 2024 @11:09AM (#39642428)
'Write me something profane?' That probably weeds out commercially available GPTs?
[ Parent | on HN ]
Re:You can now train a 70B language model at home by rthnbgrredf on Friday March 08, 2024 @02:26PM (#39645141)
I'm sorry, but I can't fulfill that request. Is there anything else I might assist you with? ;)
[ Parent | on HN ]
Re:You can now train a 70B language model at home by int_19h on Friday March 08, 2024 @02:52PM (#39645516)
https://chirper.ai/aligned/chirp/65e58aa9001d853c
[ Parent | on HN ]
Re:You can now train a 70B language model at home by natch on Saturday March 09, 2024 @02:21AM (#39650084)
No, this is a common fallacy. You can tell ChatGPT, one of the most infamously hobbled GPTs, in custom instructions that you do want profanity, and it will oblige. This is not a jailbreak, this is supported behavior.
[ Parent | on HN ]
Re:You can now train a 70B language model at home by rthnbgrredf on Saturday March 09, 2024 @03:49AM (#39650405)
I do think that there is a certain amount of gpt bot activity present on HN. But I don't think it makes sense to call people out and saying they are a gpt just based on one comment.
[ Parent | on HN ]