Conversation
Add a new `assistant.system_prompt_sections` entry instructing the
assistant to back two shapes of claim with a tool call in the same
turn rather than memory: counts/exhaustiveness ("only three callers",
"that's all of them") and claimed inability ("I can't do X from
here"). Both are pointed out as failure modes where confidence comes
from whatever happens to be in context, not from an actual search.
The section frames the distinction as behavior vs. scope: a test can
back a behavioral claim, but a claim about how many or where requires
a grep, and recommends hedged phrasing ("at least three that I've
seen") when a full search isn't practical.
Signed-off-by: Jean Mertz <git@jeanmertz.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a new
assistant.system_prompt_sectionsentry instructing the assistant to back two shapes of claim with a tool call in the same turn rather than memory: counts/exhaustiveness ("only three callers", "that's all of them") and claimed inability ("I can't do X from here"). Both are pointed out as failure modes where confidence comes from whatever happens to be in context, not from an actual search.The section frames the distinction as behavior vs. scope: a test can back a behavioral claim, but a claim about how many or where requires a grep, and recommends hedged phrasing ("at least three that I've seen") when a full search isn't practical.