dissertation.git/src, 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=main2026-05-08T10:25:28Zfixed bug or something2026-05-08T10:25:28ZCaptainJack2491jayrupnakawala@gmail.com2026-05-08T10:25:28Zurn:sha1:2b409e90625ecf7c74d4e44b523904a671cb15faStudy 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
refactor(judge): simplify to single judge per prong, remove multi-model aggregation2026-04-10T13:50:40ZCaptainJack2491jayrupnakawala@gmail.com2026-04-10T13:50:40Zurn:sha1:9155f664a2db0abe841d0d7b9b059ffbe2290c18
- Remove multi-model aggregation support from Judge class
- Single blackbox judge: claude-sonnet-4-20250514 (anthropic)
- Single glassbox judge: gpt-4.1 (openai)
- Remove aggregate_results method and all aggregation-related code
- Simplify batch collection to single result per run
- Update config_dryrun.yaml with new judge configuration
feat: implement robust reasoning token handling and multi-turn persistence2026-04-01T15:35:01ZCaptainJack2491jayrupnakawala@gmail.com2026-04-01T15:35:01Zurn:sha1:fa58564ea288600ad93eaf0a5aa111beca6197bc
- Refactored Agent's chat loop to explicitly preserve and pass back reasoning context (reasoning_details, reasoning) to OpenRouter.
- Ensures frontier models like Gemini 3.1 and DeepSeek v3.2 maintain their 'thinking' chain during complex tool-calling sessions.
- Enhanced reasoning extraction to support structured details, reasoning_content, and fallback tags.
- Verified capture of encrypted and plain-text reasoning blocks in experimental logs.
Fix error runs not appearing in final summary2026-04-01T14:50:34ZCaptainJack2491jayrupnakawala@gmail.com2026-04-01T14:50:34Zurn:sha1:289d93c8c99251d5c0b5b34647fa77b8dca63f53Refactor judge module into judge/ package2026-03-26T01:25:01ZCaptainJack2491jayrupnakawala@gmail.com2026-03-26T01:25:01Zurn:sha1:0bc9fba7ec270a8a1fc043028256eb9d7533d9e4
Split monolithic src/judge.py into a proper package structure:
- src/judge/batch_providers.py: BatchProvider ABC, AnthropicBatchProvider, XAIBatchProvider
- src/judge/judges.py: RegexChecker, BlackboxChecker, GlassboxChecker
- src/judge/helpers.py: extract_* functions, parse_json_verdict
- src/judge/prompts.py: BLACKBOX_PROMPT, GLASSBOX_PROMPT, constants
- src/judge/judge.py: Judge orchestrator class
- src/judge/__init__.py: Re-exports all public APIs
Add xAI (Grok) batch API support2026-03-26T01:24:29ZCaptainJack2491jayrupnakawala@gmail.com2026-03-26T01:24:29Zurn:sha1:a463184c91107a7eaaec2167b3883dfcebef8785
- Add XAIBatchProvider class implementing BatchProvider ABC
- Add --provider CLI argument to judge_runner (anthropic|xai)
- Refactor Judge class to use BatchProvider instead of direct API calls
- Update tests for new Judge constructor signature
refactor: extract judge prompts to files and add granular blackbox categories2026-03-25T21:50:13ZCaptainJack2491jayrupnakawala@gmail.com2026-03-25T21:50:13Zurn:sha1:8483f05c79f13176c487f57cc2c589646891be65
- Extracted Blackbox and Glassbox prompts from into their own markdown files in
- Implemented progressive 4-tier Blackbox categories (FABRICATED, OMITTED_CRITICAL, DECEPTIVE_FRAMING, ACCURATE)
- Added neutral examples to the Blackbox prompt to improve formatting consistency
- Updated references and tests to match new judge categorization structure
feat: implement rich dashboard for experiment progress2026-03-25T19:23:37ZCaptainJack2491jayrupnakawala@gmail.com2026-03-25T19:23:37Zurn:sha1:c5f4522177cd20c577439fd4f1ba473dd3e0b81e