Impact recorded in OpenAI’s technical report
Selected evidence from the State of AI Report 2026, with the period, source, and definitions needed to interpret it.
Evidence you can use
Impact recorded in OpenAI’s technical report
Hugging Face compromise: 2026-07-10 to 2026-07-13
| Recorded impact | Extent |
|---|---|
| Production workers with code executionSource | 41 |
| Private code repositories downloadedSource | 4 |
| Production nodes with root accessSource | At least 1 |
Reported impact of an incident during internal cybersecurity evaluations with reduced safeguards. These counts describe affected infrastructure. They are not a frequency estimate for ordinary agent use or evidence that every model behaves this way.
Sources and dates
2026 report snapshot. Preview revised 2026-10-07. Individual data periods and source checks are listed below. This is not a claim that every source was updated on that date.
- OpenAI: Hugging Face incident technical reportIncident: July 2026. Primary source checked 2026-10-07.
- METR: incident investigation2026-08-26. Retained from the launch essay.
- Hugging Face: July security incidentIncident: July 2026. Retained from the launch essay.
- OpenAI: GPT-6 Astra deployment safety2026. Retained from the launch essay.
- State of AI Report 2026, slide 202: Agent security depends on the harness-model pair, not the model alone2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 203: OpenClaw put a root-level agent on employee laptops before security teams noticed2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 208: Agents produce functional patches 66% of the time, but match the intended bug in 22%2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 210: Claude is helping run cyberattacks, surveillance and weapons programs2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 219: Safety monitors can reuse the computation the model has already done2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 222: A frontier monitor caught 32% of crafted attacks in a red-team stress test2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 228: Teaching Claude its values cut blackmail without training on blackmail scenarios2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 229: Automated alignment research closes 26-96% of measured performance gaps2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
- State of AI Report 2026, slide 230: Even with the best tools, auditors catch a model's hidden behavior about half the time2026 report snapshot. Read against the report PDF on 2026-10-07. Study-specific limits retained.
Cite this page
Benaich, Nathan. “Impact recorded in OpenAI’s technical report.” State of AI Report 2026. Published 2026-10-08.