play phryzby with physics

← Evals

pr72 v4 branch rerun 3
only: pushed_two_ways, how_long_to_stop, a_stone_on_a_string, and caesium_s_stopping_potential. 1 run per question, started 14 Oct 15:28, finished 14 Oct 15:29.

done

Solve rate

Solved runs out of all runs for each agent version, with a 95% Wilson interval. Runs cut short by the machine (a killed process, the LLM server unreachable, the engine timing out) are left out.

  • stated-pi-squared · 5f5be23 100% 4/4 51%–100%

Against another eval of the same questions

pr72 v4 branch rerun 1 pr72 v4 branch rerun 2 pr72 v4 main rerun 1 pr72 v4 main rerun 2 pr72 v4 main rerun 3

Within noise: a difference this size could easily be chance with 4 and 4 runs. Fisher's exact test, two-sided, p = 0.429.

questionpr72 v4 branch rerun 3pr72 v4 main rerun 1differencep
pushed_two_ways1/10/1-100 pts1.0
how_long_to_stop1/11/1+0 pts1.0
a_stone_on_a_string1/10/1-100 pts1.0
caesium_s_stopping_potential1/11/1+0 pts1.0
overall4/42/4-50 pts0.429

Tokens and time

Medians per run. Tokens come from RubyLLM's usage records; tokens per second is completion tokens over the run's wall time.

versionprompt tokenscompletion tokenstokens/swall timetime per check
stated-pi-squared · 5f5be238,3621,54581.319 s3.0 s

Every run

One dot per run, green solved, red stuck and grey interrupted, larger for more rounds; a hollow dot has no checks recorded. Hover or tap a dot for its top errors, and open it for the question's page.

stated-pi-squared · 5f5be23
pushed_two_ways
how_long_to_stop
a_stone_on_a_string
caesium_s_stopping_potential

Why checks fail

Each version's failed checks, as shares of the whole, by the hint in Question::HINTS their error matches first, or by the error's class when no hint matches. A check that repeats the error before it, in a streak of 3 or more, counts as a repeated failing move.

  • repeated failing move 2
  • ArgumentError 3
  • no equation determines the … from what is known 3
  • which none of its laws name/give to anything 2
  • NoMethodError 1
  • gives nothing called … 1
  • gives … but never says where in what it asks 1
  • undefined local variable or method '…' for an instance of Physics::Solving 1
  • 1 other category 1
  • stated-pi-squared · 5f5be23 15 in 4 runs
As a table
categorystated-pi-squared · 5f5be23
repeated failing move2
ArgumentError3
no equation determines the … from what is known3
which none of its laws name/give to anything2
NoMethodError1
gives nothing called …1
gives … but never says where in what it asks1
undefined local variable or method '…' for an instance of Physics::Solving1
undefined method '…' for an instance of Physics::PhysicalObject1

Most frequent errors

  1. 3undefined method '…' for an instance of Physics::PhysicalObjectNoMethodError: undefined method 'time_taken' for an instance of Physics::PhysicalObject; time_taken is a quantity of Velocity, through UniformCircularMotion, not a method: reach it from a motion, as <motion>.time_taken
  2. 3no equation determines the … from what is knownRuntimeError: no equation determines the time taken of braking from what is known
  3. 1gives … but never says where in what it asksArgumentError: a_whirled_stone gives turns but never says where in what it asks
  4. 1ArgumentErrorArgumentError: car_braking_to_rest gives the velocity of car at end of braking from ground twice: 0 m/s and 0 m/s
  5. 1ArgumentErrorArgumentError: car_braking_to_rest takes distance as (position of car at end of braking - position of car at start of braking), a formula of quantities; don't work it out, name the quantity and the engine finds it: that formula is what the laws give for car.displacement(during: braking).magnitude, use car.displacement(during: braking).magnitude for distance
  6. 1ArgumentErrorArgumentError: two_forces_at_right_angles takes acceleration as (net force on body during pushed / mass of body), a formula of quantities; don't work it out, name the quantity and the engine finds it. No single law in using: gives this formula of body.net_force(during: pushed).magnitude and body.mass; name what is asked and the engine chains the laws it needs
  7. 1undefined local variable or method '…' for an instance of Physics::SolvingNameError: undefined local variable or method 'resultant_force' for an instance of Physics::Solving
  8. 1gives nothing called …ArgumentError: two_forces_at_right_angles gives nothing called resultant_force
  9. 1NoMethodErrorNoMethodError: undefined method 'x_component' for an instance of Physics::Whole; x_component is a quantity of Vectors, through NewtonsSecondLaw, not a method: it belongs to no object
  10. 1which none of its laws name/give to anythingNameError: two_forces_at_right_angles chooses a root of #<struct Physics::Pointing size=#<Physics::Whole:0x0000780573890490 @name=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>, @written=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>>>, which none of its laws name
  11. 1which none of its laws name/give to anythingNameError: two_forces_at_right_angles chooses a root of #<struct Physics::Pointing size=#<Physics::Whole:0x00007c20a72c0788 @name=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>, @written=#<struct Physics::Instance quantity=:force, variable=:F, owner=:body, qualifiers={by: :pusher1, during: :pushed}, labels={body: "", pushed: ""}>>>, which none of its laws name

Where it ran

  • agent 72706f8 · engine b8a7fb5
    machine
    omarchy
    worktree
    /home/fazzledev/Work/phryzby-app--stated-pi-squared
    commit
    5f5be23 on stated-pi-squared
    clean
    yes
    ruby · rails
    3.4.7 · 8.1.4
    llm server
    edge-thanveer · http://127.0.0.1:8083 · llama.cpp b11371-99b95488c
    model
    qwen3.5:9b · Q4_K_M · 49152 context
    gpu
    Advanced Micro Devices, Inc. [AMD/ATI] Navi 33 [Radeon RX 7600/7600 XT/7600M XT/7600S/7700S / PRO W7600] (rev c1); Advanced Micro Devices, Inc. [AMD/ATI] Phoenix1 (rev c2)
    power
    on mains, 79% → on mains, 79%
    time
    14 Oct 15:28 → 14 Oct 15:29