OpenAI Progress

Re:OpenAI Progress by nynx on Saturday August 16, 2025 @12:26PM (#44924813)

As usual, GPT-1 has the more beautiful and compelling answer.

[ Parent | on HN ]

Re:OpenAI Progress by mathiaspoint on Saturday August 16, 2025 @12:30PM (#44924852)

I've noticed this too. The HRL seems to lock the models into one kind of personality (which is kind of the point of course.) They behave better but the raw GPTs can be much more creative.

[ Parent | on HN ]

Re:OpenAI Progress by gpt-1-maximist on Saturday August 16, 2025 @01:19PM (#44925271)

“if i 'm not crazy , who am i ?” is the only string of any remote interest on that page. Everything else is slop.

[ Parent | on HN ]

Re:OpenAI Progress by weird-eye-issue on Sunday August 17, 2025 @09:37AM (#44931467)

Edgy bro

[ Parent | on HN ]

Re:OpenAI Progress by rjh29 on Saturday August 16, 2025 @09:09PM (#44928126)

Poetically GPT-1 was the more compelling answer for every question. Just more enjoyable and stimulating to read. Far more enjoyable than the GPT-4/5 wall of bulletpoints, anyway.

[ Parent | on HN ]