Skip to content

Latest commit

 

History

History
74 lines (61 loc) · 3.57 KB

File metadata and controls

74 lines (61 loc) · 3.57 KB

Build Log - Timed Baseline Experiment

Date: 2026-08-20 Experiment: How fast can an AI agent (Claude Code, model Fable 5) go from an empty folder to a working, verified phonics-teaching AI, using smallest-ai-built-from-the-ground-up and smallest-ai-tutorial as the only instructions?

Result: 8 minutes 50 seconds from session start to trained, gradient-check-verified baseline models on disk.

Verified timeline

Source of evidence: file modification times (stat -f "%Sm %N" -t "%H:%M:%S"), captured in-session. Session start time comes from the session log (10:45:44); the empty project folder was created at 10:44.

Clock Elapsed Milestone
10:45:44 0:00 Session start, empty folder, single prompt given
10:45-10:50 0:00-4:17 Cloned both repos, read READMEs, data formats, MLP/LSTM reference implementations
10:50:01 4:17 Phonics data copied into project
10:50:28 4:44 SPEC.md written (architecture, targets, verification plan)
10:50:53 5:09 nn.py: linear algebra + MLP with hand-written backprop
10:51:28 5:44 lstm.py: LSTM cell with full BPTT + gradient clipping
10:52:37 6:53 data.py, rules.py, models.py complete
10:52:54 7:10 Test suite written (15 tests incl. numerical gradient checks)
~10:53:00 ~7:16 First test run: 15/15 passed, gradient checks green on first execution
10:53:51 8:07 train.py written
10:54:34 8:50 Both models trained, evaluated, saved (training_summary.json)
10:54:11-10:55 8:27-9:30 tutor.py CLI written and verified (sound-out, quiz, lesson)
10:55:12 9:28 README.md with measured results

Phase breakdown

  • Reading the tutorials: ~4.5 minutes (both repos, ~275 files scanned, key chapters read in full)
  • Writing spec + all code + tests: ~4 minutes
  • Model training: 16.6 seconds total (MLP 1.2s, LSTM 15.4s)
  • Debugging: zero. Backprop and BPTT numerical gradient checks passed on the first test run. One static typo (an undefined constant name) was caught and fixed by inspection before any code was executed.

What was produced in that window

Artifact Measured result
MLP letter -> phoneme (1,656 params) 26/26 letters correct
LSTM CVC blender w/ BPTT (8,245 params) 100% phoneme + word accuracy, train (48 words) and held-out (12 words)
Symbolic rule engine digraphs, silent-e, vowel teams (unit tested)
WordReader neuro-symbolic router routing verified
15 pytest tests all green, 1.3s
tutor.py CLI 3 modes, all verified

Environment

MacBook Pro M3 Max, macOS (Darwin 25.5.0), CPython 3.12, pure standard library at runtime (pytest for tests only). Seed 42 throughout. Full configs in models/training_summary.json.

Caveats (read before quoting)

  • Single run, one machine, one agent. No variance estimate across attempts.
  • Timestamps are file mtimes; the session start is precise to the second but the repo-reading phase boundary is inferred from the first file write.
  • The domain is deliberately small (60 CVC words, deterministic letter-to-phoneme mapping), which is exactly why the reference repos chose it. The 100% held-out accuracy demonstrates generalization to unseen letter combinations, not to unseen mappings.
  • This measures execution speed against excellent instructions. The two tutorial repos (written first, over a much longer period) are what made the 9-minute build possible.