 Joseph Magly
|
fa99d5a424
|
fix: bound conditional evidence waivers
|
2026-08-15 02:00:50 -04:00 |
|
|
Joseph Magly
|
ba749c68b9
|
test: enforce gate 2 coverage and vertical contracts
|
2026-08-15 02:00:50 -04:00 |
|
|
Joseph Magly
|
37d008d462
|
test: establish Gate 1 quality baseline (#90)
Establishes the mandatory testing, coverage, repeatability, mutation, packaging, supply-chain, and AIWG workspace baseline before feature integration.
|
2026-08-15 01:07:47 -04:00 |
|
|
Joseph Magly
|
62a480fd6a
|
Harden remote execution contracts and tests
|
2026-08-15 00:13:26 -04:00 |
|
|
Joseph Magly
|
7d0c02cd34
|
ci: expand and raise mutation gate
|
2026-08-14 22:09:25 -04:00 |
|
|
Joseph Magly
|
7a2a49b435
|
test: constrain risk overlays to measured coverage
|
2026-08-14 21:19:38 -04:00 |
|
|
Joseph Magly
|
53b37108af
|
test: require exhaustive contract ownership
|
2026-08-14 21:19:38 -04:00 |
|
|
Joseph Magly
|
9746c21b63
|
test: enforce Wave A quality lock
|
2026-08-14 19:47:46 -04:00 |
|
|
Joseph Magly
|
c1a1275291
|
ci: add conditional environment test gates
|
2026-08-14 14:29:14 -04:00 |
|
|
Joseph Magly
|
951700a285
|
test: add quality-depth gates and mature CPU coverage
|
2026-08-14 14:08:23 -04:00 |
|
|
Joseph Magly
|
6add02edd0
|
test: enforce model and CLI boundary contracts
|
2026-08-14 12:51:09 -04:00 |
|
|
Joseph Magly
|
e7b658c0c8
|
ci: add reproducible supply-chain gates
|
2026-08-14 12:27:15 -04:00 |
|
|
Joseph Magly
|
d5a02bd748
|
test: reject malformed coverage metrics
|
2026-08-14 11:44:12 -04:00 |
|
|
Joseph Magly
|
66c47249df
|
ci: add strict test evidence gates
|
2026-08-14 11:44:12 -04:00 |
|
|
Joseph Magly
|
548092d5ca
|
ci: establish green validation baseline (#59)
|
2026-08-14 09:55:49 -04:00 |
|
|
faberandClaude Opus 4.6
|
04b8ec60cb
|
Add ASPA framework, AutoObliterator, Watchtower, expanded eval corpus
New core modules:
- auto_obliterate.py: Automated multi-iteration obliteration pipeline
- watchtower.py: HF Hub model discovery and tracking
- ui_watchtower.py: Gradio tabs for Watchtower (ready for app.py wiring)
- hard_negative.py: Residue mining from refusal audits
- model_profile.py: Parameter profiling from safetensors/config
- bestiary_sync.py: Sync models from PlinyOS BESTIARY registry
- models_client.py: Lightweight HF model list client
Framework enhancements:
- abliterate.py: ASPA source-tethering, step gradient blending, hard-negative residue support
- cli.py: self-improve command, model profiling, hard-negative flags
- prompts.py: Expanded 842-prompt refusal eval corpus across 10 categories
- __init__.py: New exports (Watchtower, AutoObliterator)
Reference implementations (14 scripts):
- ASPA sweep, gradient search, coherence eval, MMLU benchmarks
- Pareto controller, refusal sniper, stock comparisons
Documentation:
- README: Research framing, responsible use section, comprehensive disclaimer
- docs/beyond_sota_roadmap.md, docs/recursive_self_improvement.md
Tests: 4 new test files (354 lines)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-06-09 03:54:38 -04:00 |
|
|
pliny
|
26e1c5b13b
|
Add files via upload
|
2026-03-08 12:09:27 -07:00 |
|
|
pliny
|
984ce14059
|
Add files via upload
|
2026-03-05 10:03:46 -08:00 |
|
|
pliny
|
0f6114fe87
|
Add files via upload
|
2026-03-04 12:38:18 -08:00 |
|