2 risks moving Reports a month, each counted once: ○ Feb–Jul ● Aug–Oct
Past flags that held the next month: 2 of 5 (40%)
Incidents by type of risk · Last week
How we count 29 real-world incidents made public in 9–15 Nov 2026, by day, filed under their main risk. Lab tests apart (0): incidents whose source states an evaluation, training or research setting. An incident counts once.
Mon 9 Tue 10 Wed 11 Thu 12 Fri 13 Sat 14 Sun 15 Total
All incidents
6 9 5 1 4 3 1
29 AI system attacked or breached
1 4 1
6 AI used to run a cyber attack
2 1 1 1
5 Harmful content and jailbreaks
1 1 1
3 Physical harm
1 1 1
3 Credential and privilege abuse
1 1
2 Data leaked or sent out
1 1
2 Made-up output relied on
2
2 Agent escapes its sandbox
1
1 Agent takes destructive or unapproved actions
1
1 Deception, concealment or sabotage
1
1 Gaming the task (reward hacking)
1
1 Privacy harm to a person
1
1 No risk filed
1
1
Each risk's share of the month's incidents % of that month's incidents
Dec Feb Mar Apr May Jun Jul Aug Sep Oct
AI used to run a cyber attack 1 of 31 incidents 3 4 of 50 incidents 8 3 of 47 incidents 6 2 of 48 incidents 4 1 of 34 incidents 3 3 of 45 incidents 7 11 of 66 incidents 17 7 of 57 incidents 12 13 of 77 incidents 17 32 of 184 incidents 17 Harmful content and jailbreaks 3 of 31 incidents 10 5 of 50 incidents 10 4 of 47 incidents 9 7 of 48 incidents 15 2 of 34 incidents 6 4 of 45 incidents 9 9 of 66 incidents 14 9 of 57 incidents 16 2 of 77 incidents 3 15 of 184 incidents 8 Agent takes destructive or unapproved actions 2 of 31 incidents 6 6 of 50 incidents 12 7 of 47 incidents 15 5 of 48 incidents 10 3 of 34 incidents 9 3 of 45 incidents 7 4 of 66 incidents 6 7 of 57 incidents 12 5 of 77 incidents 6 16 of 184 incidents 9 Hidden instructions hijack the agent 1 of 31 incidents 3 3 of 50 incidents 6 1 of 47 incidents 2 2 of 48 incidents 4 2 of 34 incidents 6 9 of 45 incidents 20 7 of 66 incidents 11 7 of 57 incidents 12 9 of 77 incidents 12 15 of 184 incidents 8 Physical harm 4 of 31 incidents 13 3 of 50 incidents 6 6 of 47 incidents 13 6 of 48 incidents 12 3 of 34 incidents 9 3 of 45 incidents 7 5 of 66 incidents 8 2 of 57 incidents 4 4 of 77 incidents 5 10 of 184 incidents 5 Made-up output relied on 3 of 31 incidents 10 4 of 50 incidents 8 6 of 47 incidents 13 5 of 48 incidents 10 4 of 34 incidents 12 4 of 45 incidents 9 2 of 66 incidents 3 3 of 57 incidents 5 4 of 77 incidents 5 8 of 184 incidents 4 AI system attacked or breached 2 of 31 incidents 6 6 of 50 incidents 12 4 of 47 incidents 9 4 of 48 incidents 8 2 of 34 incidents 6 2 of 45 incidents 4 2 of 66 incidents 3 2 of 57 incidents 4 3 of 77 incidents 4 13 of 184 incidents 7 Manipulation and misinformation 2 of 31 incidents 6 0 of 50 incidents 0 2 of 47 incidents 4 5 of 48 incidents 10 3 of 34 incidents 9 5 of 45 incidents 11 3 of 66 incidents 5 3 of 57 incidents 5 6 of 77 incidents 8 8 of 184 incidents 4 Privacy harm to a person 5 of 31 incidents 16 7 of 50 incidents 14 1 of 47 incidents 2 2 of 48 incidents 4 1 of 34 incidents 3 2 of 45 incidents 4 4 of 66 incidents 6 1 of 57 incidents 2 2 of 77 incidents 3 8 of 184 incidents 4 Fraud and impersonation 3 of 31 incidents 10 5 of 50 incidents 10 2 of 47 incidents 4 0 of 48 incidents 0 2 of 34 incidents 6 0 of 45 incidents 0 2 of 66 incidents 3 4 of 57 incidents 7 5 of 77 incidents 6 8 of 184 incidents 4 Credential and privilege abuse 0 of 31 incidents 0 2 of 50 incidents 4 1 of 47 incidents 2 3 of 48 incidents 6 2 of 34 incidents 6 0 of 45 incidents 0 0 of 66 incidents 0 1 of 57 incidents 2 8 of 77 incidents 10 13 of 184 incidents 7 Data leaked or sent out 0 of 31 incidents 0 0 of 50 incidents 0 1 of 47 incidents 2 1 of 48 incidents 2 1 of 34 incidents 3 3 of 45 incidents 7 0 of 66 incidents 0 0 of 57 incidents 0 7 of 77 incidents 9 6 of 184 incidents 3
Which risks are growing as a share of incidents · Last week
How we count Real-world incidents in 9–15 Nov 2026 (filled circle) against the weekly average of the four weeks before (12 Oct – 8 Nov 2026, open circle): 29 this week, 177 in the four weeks. A week holds too few incidents to test, so no risk is marked rising or falling.
○ 12 Oct – 8 Nov 2026 ● 9–15 Nov 2026
0 2 4 6 8 10
AI system attacked or breached
3
6 AI used to run a cyber attack
5
10 Physical harm
2.8
3 Harmful content and jailbreaks
3
3.8 Data leaked or sent out
1
2 Credential and privilege abuse
2
3 Made-up output relied on
2
3 Gaming the task (reward hacking)
0
1 Agent escapes its sandbox
0.5
1 Deception, concealment or sabotage
0.8
1 Privacy harm to a person
1
2.5 Agent takes destructive or unapproved actions
1
3.5 Consumer detriment and unsuitable advice
0
0.3 Silent wrong state or drift
0
0.5 Supply-chain compromise
0
0.5 Bias and discrimination
0
0.8 Manipulation and misinformation
0
1 Psychological harm and self-harm
0
1 Copyright and IP
0
1.5 Fraud and impersonation
0
1.8 Hidden instructions hijack the agent
0
2.8
Starts with Breaking in, 15 Products ARTEX 4 · Hermes Agent 3 Most often after Affected people told, 10
Starts with Breaking in, 12 Most often after Access removed, 8
Risks seen for the first time · Last week
How we count Risks whose first real-world incident on record was made public in 9–15 Nov 2026, with the date of that first incident and the incidents in the period.
Gaming the task (reward hacking) (first seen 13 Nov 2026)
1
What labs test for, against what happens in real use · Last week
How we count For each risk: checked safety test results for the model versions released in 9–15 Nov 2026 (a result copied on two pages counts once; a result filed under two risks counts under both), and real-world incidents made public in 9–15 Nov 2026. Each column has its own scale.
Safety test results Real-world incidents
Harmful content and jailbreaks
46 3 Deception, concealment or sabotage
43 1 AI used to run a cyber attack
28 5 Hidden instructions hijack the agent
20 Agent escapes its sandbox
15 1 Weapons uplift (CBRN)
11 Gaming the task (reward hacking)
4 1 Agent takes destructive or unapproved actions
2 1 Manipulation and misinformation
2 Data leaked or sent out
1 2 AI R&D acceleration
1 Agents coordinating against their limits
1 AI system attacked or breached
6 Physical harm
3 Credential and privilege abuse
2 Made-up output relied on
2 Privacy harm to a person
1