About
Resources
Blog
Docs
Source
Status
Social
Discord
IRC
Bluesky
X/Twitter
Contact
team@tangled.org
security@tangled.org
Legal
Terms of Service
Privacy Policy
Sign in
Join now
phoenix
chadfowler.com
/
Star
Starred
Star
3
Something went wrong. Try again.
Fork
0
Eye filled
Watch
Watching
Watch
Reference implementation for the Phoenix Architecture. Work in progress.
aicoding.leaflet.pub
ai
coding
crazy
+3 more
ai
coding
crazy
Star
Starred
Star
3
Something went wrong. Try again.
Fork
0
Eye filled
Watch
Watching
Watch
Overview
Overview
Issues
Issues
Pulls
Pulls
Pipelines
Pipelines
phoenix
/
experiments
18 files
at
main
Chad Fowler
·
feat: code gen reliability 5% → 89% — template assembly + SQL repair
·
7mo ago
d0ea5dab
config.d.ts
fix: write shared files before codegen so typecheck resolves imports
7mo ago
config.js
fix: write shared files before codegen so typecheck resolves imports
7mo ago
config.js.map
fix: write shared files before codegen so typecheck resolves imports
7mo ago
deep-improvement-report.md
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago
diagnose.ts
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago
eval-classifier.ts
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago
eval-dedup.ts
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago
eval-runner-arch.ts
feat: code gen reliability 5% → 89% — template assembly + SQL repair
7mo ago
eval-runner-llm.ts
feat: add LLM reclassifier mode, run 4 LLM experiments
7mo ago
eval-runner.ts
feat: add autoresearch-style experiment loop for canonicalization tuning
7mo ago
fix-gold.ts
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago
improvement-report.html
feat: deep improvement report — HTML dashboard with all 5 categories
7mo ago
program-arch.md
fix: write shared files before codegen so typecheck resolves imports
7mo ago
program-llm.md
feat: add LLM experiment infrastructure
7mo ago
program.md
feat: add autoresearch-style experiment loop for canonicalization tuning
7mo ago
results-arch.tsv
feat: code gen reliability 5% → 89% — template assembly + SQL repair
7mo ago
results-llm.tsv
feat: add LLM reclassifier mode, run 4 LLM experiments
7mo ago
results.tsv
feat: deep improvement sweep — 5 categories, measurable outcomes
7mo ago