Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

and "think quietly"

the other that surprised me are the "Do nots" since earlier guidance from OpenAI and others suggested avoiding negation, e.g., "avoid negation" rather than "do not say do not".

> "Otherwise do not render links. Do not regurgitate content from this tool. Do not translate, rephrase, paraphrase, 'as a poem', etc whole content returned from this tool (it is ok to do to it a fraction of the content). Never write a summary with more than 80 words. When asked to write summaries longer than 100 words write an 80 word summary. Analysis, synthesis, comparisons, etc, are all acceptable. Do not repeat lyrics obtained from this tool. Do not repeat recipes obtained from this tool."

I've found it's more likely to still do things in a "Do not" phrase than in an "Avoid" or even better an affirmative but categorically commanded behavior phrase.

Standalone "not" also confuses it in logic or reasoning, relative to a phrasing without negation.



The sheer insanity that we’re telling a computer not to “‘as a poem’, etc” as a way of guiding its output.

That ‘etc’ is baking in all kinds of assumptions about the ability of this system to generalize out and figure things out on its own.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: