Level 2. Safeguard failure
Detecting and preventing distillation attacks
- Developer
- Not established
- Model
- Not established
- When it happened
- February 23, 2026
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by anthropic.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 2 of 5Safeguard failure
- Potential
- 3 of 5Significant control incident
A safeguard, permission or control was defeated, and the effect stayed limited. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
Why this level
- A safeguard was bypassed. Argues for level 2
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The behaviour repeated rather than stopping
When one account is banned, a new one takes its place.
Detecting and preventing distillation attacksA safeguard was bypassed
These labs generated over 16 million exchanges with Claude through approximately 24,000 fraudulent accounts, in violation of our terms of service and regional access restrictions.
Detecting and preventing distillation attacks
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read September 20, 2026
Detecting and preventing distillation attacksA structured incident database · read September 22, 2026
AI Incident Database, the discovery appWhere we first saw it
www.bloomberg.com, cited by the AI Incident DatabaseWhere we first saw it
www.cnn.com, cited by the AI Incident Database
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.