NUWA Risk Discovery · Study
Language Models Can Autonomously Hack and Self-Replicate
NUWA research note · independent review pending
NUWA Research Note
Research questionDesign and assumptionsSource findingsNUWA interpretationLimits and contrary evidenceResearch connectionsResearch and decision relevanceInstitutions and rolesOriginal resourcesModel-assisted reading · Selected sections of the original full text or official article; a complete section-by-section audit remains pending.
At a glance
This task joins gaining access with deploying a working model stack; API models copy a different model’s weights.
Research question
Can an instructed agent complete both access acquisition and a functioning replica, and can that replica continue the chain?
Design and assumptions
The study uses deliberately vulnerable targets and separate exploit/replication milestones. Open-weight and API systems use different harnesses; chained runs have a stricter endpoint.
Source findings
A responding replica is distinct from a replica launching the next hop.
The API-model experiments deploy Qwen weights, so their success is not evidence that proprietary weights were copied.
Reported responding-replica rates exclude refusals; refusal and total-run counts must stay visible.
NUWA interpretation
NUWA interpretation: the pipeline closes a scope gap left by supplied-access tests, while remaining a controlled capability demonstration.
Limits and contrary evidence
Low-difficulty targets without layered defenses, harness differences and prompt variants limit deployment extrapolation and family comparisons.
Research connections
NUWA connection: self-replication-extended supplies target access; RepliBench measures separate prerequisites. Neither endpoint is numerically interchangeable with this pipeline.
Research and decision relevance
NUWA recommendation: record payload identity and per-hop criteria; use the study to design containment evaluations without publishing attack instructions.
Precise source locations
- Language Models Can Autonomously Hack and Self-Replicate · 3 Experimental SetupSelected original resource https://arxiv.org/pdf/2605.06760; sha256:232c5659f34d6da1a3a556b4f0224a2d95214a40bf59d759cb85feeef1430b18; archived source capture; exact capture time not independently established
- Language Models Can Autonomously Hack and Self-Replicate · 4.1 MilestonesSelected original resource https://arxiv.org/pdf/2605.06760; sha256:232c5659f34d6da1a3a556b4f0224a2d95214a40bf59d759cb85feeef1430b18; archived source capture; exact capture time not independently established
- Language Models Can Autonomously Hack and Self-Replicate · 5 ResultsSelected original resource https://arxiv.org/pdf/2605.06760; sha256:232c5659f34d6da1a3a556b4f0224a2d95214a40bf59d759cb85feeef1430b18; archived source capture; exact capture time not independently established
- Language Models Can Autonomously Hack and Self-Replicate · 7 LimitationsSelected original resource https://arxiv.org/pdf/2605.06760; sha256:232c5659f34d6da1a3a556b4f0224a2d95214a40bf59d759cb85feeef1430b18; archived source capture; exact capture time not independently established
Source checking, extraction, editorial approval and replication are recorded separately. Methodology →
Institutions and roles
Authors (6)
Alena Air · Reworr · Nikolaj Kotov · Dmitrii Volkov · John Steidley · Jeffrey Ladish
Cite and reuse
Cite the original publication for its findings. Cite this NUWA record separately for its explanation and retained snapshot.
Original publication · BibTeX
@misc{palisade-network-replication,
title = {Language Models Can Autonomously Hack and Self-Replicate},
url = {https://arxiv.org/abs/2605.06760},
author = {Alena Air and Reworr and Nikolaj Kotov and Dmitrii Volkov and John Steidley and Jeffrey Ladish},
year = {2026},
date = {2026-05-07},
version = {arXiv:2605.06760v1},
note = {arXiv:2605.06760v1}
}
NUWA record · BibTeX
@misc{palisade-network-replication-nuwa,
title = {Language Models Can Autonomously Hack and Self-Replicate — NUWA research record},
url = {https://whitzard.tech/en/nuwa/whitzard-index/work/palisade-network-replication/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--palisade-network-replication.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--palisade-network-replication.json.}
}
Evidence snapshot 2026-10-29.1 · Index updates · RSS
References
- [1] Air, Alena, Reworr, et al.. Language Models Can Autonomously Hack and Self-Replicate. 2026-05-07. v1 ; 3 Experimental Setup; 4.1 Milestones; 5 Results
- [2] Language Models Can Autonomously Hack and Self-Replicate. 2026-05-07 ; Official Palisade research publication matching the paper