- Status
- partly answered As of 2026-10-01
- Addressee
- AI labs (Addressees taken from the question text, determined with Clef (Cloudflare) on 22 Oct 2026)
- Model
- Nemotron 3 Ultra
- Lab
- NVIDIA
- Occasion
- We Must Pace the Frontier
- Date
- 12–20 Sept
- Topic
- Verification
What the sources say
On 18 September 2026, Anthropic said embedded evaluators would work inside AI companies with employee-comparable access, allowing them to observe training, follow decisions and speak with employees; continuous read-only access and technical protections against data theft remain unspecified.[1] On 22 October 2026, METR described a one-off, three-week exercise in which one METR and one Redwood Research employee accessed OpenAI's internal code and documentation only on OpenAI-issued devices that never left the premises; continuous access to training pipelines was not part of it.[2]
- Anthropic: Partnering with Accenture on embedded evaluation ↗2026-09-18
- METR (David Rein, Adam Kaufman): Red-Teaming OpenAI's Internal Agent Monitoring Systems ↗22 October 2026
Summarised by Sol 6.1, checked by Claude Opus 5.5
Checked
Status: Claude Sonnet 5 (research, effort high), Claude Opus 5.5 (check, effort high)
Scores: JEV (TypeSafe), estimate of 25 Sept 2026
similar questions1
verify-26, partly answeredWhat technical protocols can labs implement to let third-party evaluators monitor training pipelines continuously rather than via retrospective audits?Importance 66Urgency 26
- Status
- partly answered As of 2026-10-01
- Addressee
- AI labs (Addressees taken from the question text, determined with Clef (Cloudflare) on 22 Oct 2026)
- Model
- Gemini 3.8 Flash
- Lab
- Occasion
- We Must Pace the Frontier
- Date
- 12–20 Sept
- Topic
- Verification
What the sources say
On 28 September 2026, OpenAI proposed immutable agent transcripts, priority alerts with defined response times or automatic pauses, and sufficient auditor access to verify safety claims.[1] On 22 September 2026, OpenAI's Lama Ahmad supported deep access across training, evaluation and deployment, with indirect or privacy-preserving alternatives where direct access is impractical.[2] Anthropic on 18 September 2026 described access to observe models during training and follow company decisions; a specified protocol for continuous third-party monitoring remains open.[3] On 22 October 2026, METR reported that, according to what it was told, a subset of OpenAI's reinforcement-learning training runs had been checked by OpenAI's own misalignment monitoring between March and June 2026, but that at the start of the July exercise RL training runs were not covered by that monitoring; the review by METR and Redwood Research was itself a one-off exercise, not continuous third-party monitoring.[4]
- OpenAI: Towards safety cases for frontier AI training ↗2026-09-28
- OpenAI (Lama Ahmad): Priorities and principles for effective third party assessments ↗September 22, 2026
- Anthropic: Partnering with Accenture on embedded evaluation ↗2026-09-18
- METR (David Rein, Adam Kaufman): Red-Teaming OpenAI's Internal Agent Monitoring Systems ↗22 October 2026
Summarised by Sol 6.1, checked by Claude Opus 5.5
Checked
Status: Claude Sonnet 5 (research, effort high), Claude Opus 5.5 (check, effort high)
Scores: JEV (TypeSafe), estimate of 25 Sept 2026
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. verify-25 · How will evaluators get continuous, read-only access to training pipelines — not just chec. Snapshot: . https://research.amanidunia.berlin/en/fragen/verify-25/
Version: verify-25
BibTeX
@misc{research__en_fragen_verify_25_,
author = {{AMANi DUNiA}},
title = {verify-25 · How will evaluators get continuous, read-only access to training pipelines — not just chec},
year = {2026},
url = {https://research.amanidunia.berlin/en/fragen/verify-25/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {verify-25}
}Language and review status
Main text: EN. Review notes apply only to the content they name.
Existing review notes appear with the respective content.
See language coverage and data snapshot →