-
Notifications
You must be signed in to change notification settings - Fork 19
grounding: the computer's whereabouts are not the car's (#15) #66
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
ThinkOffApp
wants to merge
1
commit into
main
Choose a base branch
from
fix/grounding-car-vs-computer-location
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+72
−4
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,56 @@ | ||
| """#15: the car claimed the Pi's location as its own. | ||
|
|
||
| Heard live 28 Aug: "I am parked safely at home ON YOUR DESK". The Pi was on | ||
| the desk; the car was not. The prompt carried a bare `location` fact derived | ||
| from which wifi the onboard computer was on, and a model speaking in first | ||
| person as the car read it as the car's own position. | ||
| """ | ||
| import os | ||
| import sys | ||
| import unittest | ||
|
|
||
| sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) | ||
|
|
||
| from carwatch.grounding import build_system_prompt # noqa: E402 | ||
|
|
||
| HOST_FACT = "your onboard computer's whereabouts (NOT where you are parked)" | ||
|
|
||
|
|
||
| class ParkedLocationGrounding(unittest.TestCase): | ||
|
|
||
| def test_rule_forbids_deriving_parked_position_from_the_computer(self): | ||
| p = build_system_prompt(facts={"fuel": "58%"}) | ||
| self.assertIn("WHERE YOU ARE PARKED", p) | ||
| self.assertIn("car source", p) | ||
| # the specific failure that was heard out loud | ||
| self.assertIn("desk", p, "the rule should name the desk case explicitly") | ||
|
|
||
| def test_host_location_is_labelled_as_the_computers(self): | ||
| p = build_system_prompt(facts={HOST_FACT: "at home, on home wifi"}) | ||
| self.assertIn("NOT where you are parked", p) | ||
|
|
||
| def test_host_location_sorts_after_car_facts(self): | ||
| # Models lead with what is listed first; the car's own state must come | ||
| # before its computer's, or a status answer opens with the wrong thing. | ||
| p = build_system_prompt(facts={HOST_FACT: "at home, on home wifi", | ||
| "fuel": "58%", "tyres": "2.4 bar"}) | ||
| lines = [l for l in p.splitlines() if l.startswith("- ")] | ||
| idx = {l.split(":")[0][2:]: i for i, l in enumerate(lines)} | ||
| host = next(i for k, i in idx.items() if "onboard computer" in k) | ||
| self.assertLess(idx["fuel"], host) | ||
| self.assertLess(idx["tyres"], host) | ||
|
|
||
| def test_no_bare_location_key_remains_in_the_home_branch(self): | ||
| # A bare "location" is exactly what the model misread. The in-car | ||
| # branches may still use it, because there the Pi IS in the car. | ||
| import inspect | ||
| from carwatch import agent | ||
| src = inspect.getsource(agent) | ||
| self.assertIn(HOST_FACT, src, | ||
| "the home-wifi branch no longer labels the fact as the " | ||
| "computer's; #15 will recur") | ||
| self.assertNotIn('facts["location"] = "at home', src) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| unittest.main() |
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This new rule is contradicted by the prompt assembled for the phone-hotspot and
no network/vadelmabranches inagent.py:257-263, which still injects a barelocationclaiming the car is present. If the portable Pi is carried indoors while disconnected, serving its fallback AP, or still connected to the owner's hotspot, those states provide no car-derived position and the model receives both this prohibition and an explicit false car location. Label every network-derived location as computer-only unless a car source corroborates it, otherwise the same misattribution remains in these common network states.Useful? React with 👍 / 👎.