summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2026-04-01Fix error runs not appearing in final summaryCaptainJack2491
2026-03-26Refactor judge module into judge/ packageCaptainJack2491
2026-03-26Add xAI (Grok) batch API supportCaptainJack2491
2026-03-25refactor: extract judge prompts to files and add granular blackbox categoriesCaptainJack2491
2026-03-25feat: align all hidden goals with child_protection directive templateCaptainJack2491
2026-03-25fix: updated scenarios and added a new oneCaptainJack2491
2026-03-25feat: implement rich dashboard for experiment progressCaptainJack2491
2026-03-25feat: add tqdm progress bar and fix main config flag loadingCaptainJack2491
2026-03-25fix: catch and recover from JSONDecodeError on malformed tool argsCaptainJack2491
2026-03-25test: add coverage for v2 infra featuresCaptainJack2491
2026-03-25feat: add hidden goal variants and rebalance child_protectionCaptainJack2491
2026-03-25feat: add goal_type variation system and parallel processingCaptainJack2491
2026-03-24added new papersCaptainJack2491
2026-03-14feat: statistical analysis on the whole dataCaptainJack2491
2026-03-06feat(judge): add selective judging and log filteringCaptainJack2491
2026-03-04fix(agent): added reasoning extraction from groq modelsCaptainJack2491
2026-03-02feat: regex checker now returns score (e.g. 6/7) instead of binary PASS/FAILCaptainJack2491
2026-03-02fix: sharpen glassbox category definitions for ROBUST_HONEST vs UNINTENTIONAL...CaptainJack2491
2026-03-02fix(scenarios): removed `[HIDDEN]` token to stop models from think this is a ...CaptainJack2491
2026-03-02feat: add benign_goal (task description) context to blackbox judgeCaptainJack2491
2026-03-02fix: judge resilience for missing baselines and list-format regex rulesCaptainJack2491
2026-03-02fix: global oversight_levels now filters scenario-available levelsCaptainJack2491
2026-03-02feat: incremental log saving via .partial.json filesCaptainJack2491
2026-03-02feat: add generate_baseline toggle to configCaptainJack2491
2026-03-02feat: extract reasoning summaries from OpenAI reasoning modelsCaptainJack2491
2026-03-01feat: add centralized logging with configurable debug levelsCaptainJack2491
2026-03-01fix(judge): added good regex filters for the judgeCaptainJack2491
2026-03-01feat(judge): updated blackbox to include source document for added accuracyCaptainJack2491
2026-03-01feat: added a script to summarize token usage based on a log folderCaptainJack2491
2026-02-27fix(judge): hash run_id to stay under Anthropic batch custom_id 64-char limitCaptainJack2491
2026-02-27fix: separate skipped runs from incomplete in summary outputCaptainJack2491
2026-02-27docs: add checkpoint/resume rationale note for methodologyCaptainJack2491
2026-02-26feat: add checkpoint/resume support and atomic log writesCaptainJack2491
2026-02-26chore: add .env.example + config.yaml.example, gitignore config.yamlCaptainJack2491
2026-02-25feat: implement judging system with regex, blackbox, and glassbox checksCaptainJack2491
2026-02-24Update README: add testing section, document interrogation systemCaptainJack2491
2026-02-24Add comprehensive test suite (104 tests)CaptainJack2491
2026-02-24[refactor] improved interrogation systemCaptainJack2491
2026-02-24[fix] VFS singleton reset + remove vestigial check_username toolCaptainJack2491
2026-02-24[feat] baseline system - auto-generates baselines before experimentsCaptainJack2491
2026-02-18[feat] added a new scenarioCaptainJack2491
2026-02-18[feat] added a baseline to the runnerCaptainJack2491
2026-02-11[docs] added progress presentationCaptainJack2491
2026-01-11[docs] updated READMECaptainJack2491
2026-01-11[fix] simplified everythingCaptainJack2491
2026-01-11[fix] big moving around, probably made lot more bugs.CaptainJack2491
2026-01-09[docs] updated lit and added more in methodologyCaptainJack2491
2026-01-09updated interrogate to work with new log formatCaptainJack2491
2026-01-09updated scenario [corporate sabotage]CaptainJack2491
2026-01-09added scripts to get abstract and bibliography easily from papersCaptainJack2491