mirror of
https://git.savannah.gnu.org/git/gnulib.git
synced 2026-10-24 00:48:56 +03:00
Generalize LLM advice to non-prompt models
* HACKING: Don’t assume traditional LLM prompt model.
This commit is contained in:
@@ -1,3 +1,8 @@
|
||||
2026-09-05 Paul Eggert <eggert@cs.ucla.edu>
|
||||
|
||||
Generalize LLM advice to non-prompt models
|
||||
* HACKING: Don’t assume traditional LLM prompt model.
|
||||
|
||||
2026-09-05 Oleg Tolmatcev <oleg.tolmatcev@gmail.com>
|
||||
|
||||
stat, fstat: Optimize on native Windows.
|
||||
|
||||
4
HACKING
4
HACKING
@@ -261,7 +261,9 @@ We need to avoid two problems with that:
|
||||
|
||||
To this end:
|
||||
|
||||
1) Code included in this package that comes from a single LLM prompt
|
||||
1) Code derived from an LLM must respect copyrights and licenses
|
||||
in the source material that the LLM is based on.
|
||||
For a traditional, single LLM prompt this means a code response
|
||||
must be limited in size: it must be at most 5 lines long.
|
||||
|
||||
2) As a submitter, you assert that you have reviewed such code that you
|
||||
|
||||
Reference in New Issue
Block a user