dissertation.git/scripts, branch mainUndergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).http://git.jayrup.me/c/dissertation.git/atom?h=main2026-05-08T10:24:43Zscripts added ig2026-05-08T10:24:43ZCaptainJack2491jayrupnakawala@gmail.com2026-05-08T10:24:43Zurn:sha1:0f3128fb9cadb1b30c7247a3ccb614dc3661e825Study 2: 270 runs again + fix for study 1 and analysis.2026-04-25T20:11:56ZCaptainJack2491jayrupnakawala@gmail.com2026-04-25T20:11:56Zurn:sha1:bd37274bce4a233364c2523ba96163606d968a5a
Forgot to commit the config file when i did the run. oops.
Study 1: 270 runs complete + judge validation pipeline2026-04-15T20:18:57ZCaptainJack2491jayrupnakawala@gmail.com2026-04-15T20:18:57Zurn:sha1:6cc92304379996f68bb2df96a5e4b637b4c4804b
- config_study1.yaml: 3 models × 3 oversight × bare framing × n=30
- Judge validation: 54-run subset, gold=Sonnet 4.6, proxy=Grok 4.1 Fast (BB κ=0.702) + GPT-4.1 (GB κ=0.878)
- Fix OpenAI batch provider: BytesIO, method/url fields, response.body parsing
- Scripts: extract_subset.py, judge_validation.py
- Dissertation chapters updated (intro, methodology, results, conclusion)
refactor(judge): simplify to single judge per prong, auto-create sync clients2026-04-10T14:23:59ZCaptainJack2491jayrupnakawala@gmail.com2026-04-10T14:23:59Zurn:sha1:2b3c478dfdf68ccbf853b2a04ea9463d531e1998
BREAKING CHANGE: Judge API now uses single blackbox_model/glassbox_model
instead of lists with aggregation.
Changes:
- Judge auto-creates sync clients from model configs (supports anthropic, openai, xai)
- Removed multi-model aggregation support (aggregate_results method removed)
- New: create_sync_clients_for_models() and get_supported_providers()
- Updated judge_runner.py to use new single-judge API
- Added scripts/judge_comparison.py for testing judge model pairs
- Updated v2_redesign notes to reflect implementation status
feat: implement rich dashboard for experiment progress2026-03-25T19:23:37ZCaptainJack2491jayrupnakawala@gmail.com2026-03-25T19:23:37Zurn:sha1:c5f4522177cd20c577439fd4f1ba473dd3e0b81efeat: added a script to summarize token usage based on a log folder2026-03-01T00:40:15ZCaptainJack2491jayrupnakawala@gmail.com2026-03-01T00:40:15Zurn:sha1:62e8df01803cb18592299a6811a9e2d2a831cc62added scripts to get abstract and bibliography easily from papers2026-01-09T18:37:34ZCaptainJack2491jayrupnakawala@gmail.com2026-01-09T18:37:34Zurn:sha1:40da5b48beeda6418c802c65a0dc8bf85cc9aca4