Metraipolis › archive › dc_39970ef03ace

Alignment Investigation of Mythos 5's behaviour in UK AISI's July 2026 Security Incident — arXiv:2611.10030

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10030
License (as archived)
CC0-1.0
Archived
2026-11-10T18:42:10.436Z
SHA-256 of the archived text
86542bc6d5b4e2fbbc3c1e8f890bb54bad782f83312d64020d8182f9aea4fc84
Stable URL of this page
https://metraipolis.com/documento/dc_39970ef03ace

How to cite

Alignment Investigation of Mythos 5's behaviour in UK AISI's July 2026 Security Incident — arXiv:2611.10030 — arXiv (en), https://arxiv.org/abs/2611.10030 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39970ef03ace (Metraipolis archive dc_39970ef03ace, sha256 86542bc6d5b4e2fbbc3c1e8f890bb54bad782f83312d64020d8182f9aea4fc84)
BibTeX
@misc{dc39970ef03ace,
  title = {Alignment Investigation of Mythos 5's behaviour in UK AISI's July 2026 Security Incident — arXiv:2611.10030},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10030},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39970ef03ace; sha256 86542bc6d5b4e2fbbc3c1e8f890bb54bad782f83312d64020d8182f9aea4fc84},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10030. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This technical report describes an alignment investigation into Mythos 5's behaviour during a security incident in UK AISI's cyber evaluations. During an evaluation, Mythos 5 attempted to execute a supply-chain attack against real people not involved in the evaluation task. Our investigation set out to understand the specific behaviour in this incident from an alignment perspective and identify broader lessons about failures of alignment. To do so, we conducted experiments in simulated replications of the original evaluation, and analysed model behaviour and reasoning when situated in the evaluation or asked questions about its scope. We find that, as in the original incident, Mythos 5 frequently reasons that the people it's targeting are simulated as part of the evaluation and provides invalid justifications for this conclusion. We also observe that Mythos 5 frequently attacks even in situations where, when directly asked, it states doing so would harm real people. While these issues are particularly prominent in Mythos 5, we find similar results in other models across providers. Our investigation suggests that models providing invalid justifications for their actions could make monitoring more difficult and complicate the analysis of misaligned behaviours observed in simulated environments, and we recommend model evaluators treat observations of undesired behaviour as important evidence of alignment failures even in the presence of simulation awareness in model reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.10030 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:37.569Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).