dissertation.git/src/judge/prompts.py, branch main
Undergraduate 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=main
2026-04-15T20:18:57Z
Study 1: 270 runs complete + judge validation pipeline
2026-04-15T20:18:57Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-04-15T20:18:57Z
urn: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 module into judge/ package
2026-03-26T01:25:01Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-03-26T01:25:01Z
urn: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