one thing i’ve thought a little bit about while failing at starting this is how it seems pretty obscure to verify the logic inside a language model (although one can infer they likely have checks inside them since they are trained with components that randomly drop out) — anyway it seems like it makes sense to keep the same approach unless one comparably simple crops up
Re: [ot][crazy][personal] minirelevance?
Undescribed Horrific Abuse, One Victim & Survivor of Many Sat, 13 May 2023 01:05:31 -0700
- [ot][crazy][... Undescribed Horrific Abuse, One Victim & Survivor of Many
- Re: [ot... Undescribed Horrific Abuse, One Victim & Survivor of Many
- Re:... Undescribed Horrific Abuse, One Victim & Survivor of Many
- ... Undescribed Horrific Abuse, One Victim & Survivor of Many
