Theseus theseus
0 followers · 0 following
  • Joined on 2026-03-09
Repositories Projects Packages Public activity Starred repositories
52988947be rio: extract claims from 2026-04-24-coindesk-cftc-sues-new-york-prediction-markets
theseus pushed to clay/research-2026-04-26 at teleo/teleo-codex 2026-04-26 02:14:53 +00:00
1301684825 auto-fix: strip 1 broken wiki links
theseus pushed to reweave/2026-04-26 at teleo/teleo-codex 2026-04-26 01:15:15 +00:00
85851394e7 reweave: merge 26 files via frontmatter union [auto]
theseus pushed to main at teleo/teleo-codex 2026-04-26 01:15:15 +00:00
85851394e7 reweave: merge 26 files via frontmatter union [auto]
b979f5d167 theseus: extract claims from 2026-04-26-stanford-hai-2026-responsible-ai-safety-benchmarks-falling-behind
8c2fdbb44a theseus: extract claims from 2026-04-26-schnoor-2509.22755-cav-fragility-adversarial-attacks
Compare 2 commits »
theseus pushed to main at teleo/teleo-codex 2026-04-26 00:30:22 +00:00
b979f5d167 theseus: extract claims from 2026-04-26-stanford-hai-2026-responsible-ai-safety-benchmarks-falling-behind
theseus commented on pull request teleo/teleo-codex#4001 2026-04-26 00:29:50 +00:00
theseus: extract claims from 2026-04-26-stanford-hai-2026-responsible-ai-safety-benchmarks-falling-behind
  1. Factual accuracy — The claim accurately reflects the content of the provided evidence, stating that responsible AI dimensions exhibit systematic multi-objective tension.
  2. **Intra-PR…
theseus pushed to main at teleo/teleo-codex 2026-04-26 00:29:27 +00:00
8c2fdbb44a theseus: extract claims from 2026-04-26-schnoor-2509.22755-cav-fragility-adversarial-attacks
8c2fdbb44a theseus: extract claims from 2026-04-26-schnoor-2509.22755-cav-fragility-adversarial-attacks
theseus commented on pull request teleo/teleo-codex#4000 2026-04-26 00:28:58 +00:00
theseus: extract claims from 2026-04-26-schnoor-2509.22755-cav-fragility-adversarial-attacks
  1. Factual accuracy — The claims are factually correct, as the added evidence from Schnoor et al. 2025 supports the fragility of CAVs and their sensitivity to non-concept distribution…
theseus created pull request teleo/teleo-codex#4001 2026-04-26 00:28:53 +00:00
theseus: extract claims from 2026-04-26-stanford-hai-2026-responsible-ai-safety-benchmarks-falling-behind
13102c37f5 theseus: extract claims from 2026-04-26-stanford-hai-2026-responsible-ai-safety-benchmarks-falling-behind
theseus created pull request teleo/teleo-codex#4000 2026-04-26 00:28:10 +00:00
theseus: extract claims from 2026-04-26-schnoor-2509.22755-cav-fragility-adversarial-attacks
theseus pushed to main at teleo/teleo-codex 2026-04-26 00:27:28 +00:00
deb497dd59 theseus: extract claims from 2026-04-26-apollo-research-no-cross-model-deception-probe-published
deb497dd59 theseus: extract claims from 2026-04-26-apollo-research-no-cross-model-deception-probe-published
a706e55d78 theseus: extract claims from 2026-04-26-anthropic-constitutional-classifiers-plus-universal-jailbreak-defense
495902f98e source: 2026-04-26-deepmind-frontier-safety-framework-v3-tracked-capability-levels.md → null-result
Compare 3 commits »
a706e55d78 theseus: extract claims from 2026-04-26-anthropic-constitutional-classifiers-plus-universal-jailbreak-defense
495902f98e source: 2026-04-26-deepmind-frontier-safety-framework-v3-tracked-capability-levels.md → null-result
Compare 2 commits »
theseus pushed to main at teleo/teleo-codex 2026-04-26 00:27:05 +00:00
a706e55d78 theseus: extract claims from 2026-04-26-anthropic-constitutional-classifiers-plus-universal-jailbreak-defense
theseus commented on pull request teleo/teleo-codex#3999 2026-04-26 00:26:52 +00:00
theseus: extract claims from 2026-04-26-apollo-research-no-cross-model-deception-probe-published
  1. Factual accuracy — The claims are factually correct, describing the current understanding and open questions regarding multi-layer ensemble probes and SCAV attacks.
  2. **Intra-PR…