Skip to content

A physics domain: light, wind and speed, with every constant stated - #34

Merged
punnerud merged 1 commit into
mainfrom
feat/physics-battery
Aug 12, 2026
Merged

A physics domain: light, wind and speed, with every constant stated#34
punnerud merged 1 commit into
mainfrom
feat/physics-battery

Conversation

@punnerud

Copy link
Copy Markdown
Owner

New battery domain per request: miles, wind speed, light travel to the Moon/Mars/Sun, around the Earth.

The rule that keeps physics inside the battery's discipline

Physics leans on constants, and constants are recall. So every constant is stated in the question text — the model is never asked to remember the speed of light or a planetary distance, it is asked to compose figures it has been handed, across units. That is precisely the failure mode this project measured models into (the exponent-guessing Fermi assembly) and built machinery for.

group shape
light_travel c and the distance stated → seconds
wind_distance mph and the mile factor stated → km over hours
around_earth equator stated → hours at v
speed_conversion mph → m/s with the factor stated

Self-grading, and it caught the author first

The tests re-derive every answer from the question's own text. That discipline fired twice before any model was graded: both mile-based answers were a factor of a thousand off (MILE_KM is already km per mile; the generator multiplied by 1000 again). Two test assumptions were also wrong where the code was right — "One mile" is spelled out, not a digit, and a test that waits for the RNG to draw the Moon tests the RNG.

Measured live against qwen3

8/8 — pinned in check_numbers.py.

14 new tests, 439 in all.

The battery's rule is that the truth is computed by the same code that renders
the question, and physics threatens the rule because it leans on constants. The
resolution: every constant is IN the question text. The model is never asked to
remember the speed of light or the distance to Mars -- it is asked to compose
figures it has been handed, across units, which is the failure mode this
project has measured models into and built machinery for.

Four groups: light travel time to the Moon, the Sun, Mars and Jupiter; wind
distance in mixed units; time around the equator; mph to metres per second.
Answers are exact Fractions; most do not terminate as decimals, and matches()
grades those at the places a sensible answer states.

The tests re-derive every answer from the question's own text, and that
discipline caught the author twice before any model was graded: both mile-based
answers were a factor of a thousand off, because MILE_KM is already kilometres
per mile and the generator multiplied by 1000 again. Two test assumptions were
also wrong where the code was right -- "One mile" is spelled out, not a digit,
and a test that waits for the RNG to draw the Moon tests the RNG.

Measured live against qwen3: 8/8, pinned.
@punnerud
punnerud merged commit 1b3b6b1 into main Aug 12, 2026
6 checks passed
@punnerud
punnerud deleted the feat/physics-battery branch August 12, 2026 17:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant