Moderation problems are easy to describe badly.
One abusive post does not prove a platform stopped moderating. One quick takedown does not prove the system is healthy either.
A better measure is capacity: how many people and technical resources are assigned to the job, how quickly reports are handled, and whether that capacity keeps pace with the size of the service.
X provides unusually concrete numbers.
The staffing cuts were measurable
In January 2024, Australia’s eSafety Commissioner published information supplied by X Corp. about staffing changes after the October 2022 acquisition of Twitter. According to the regulator, X reported a 30% reduction in global trust-and-safety staff, an 80% reduction in trust-and-safety engineers, a 52% reduction in directly employed content moderators, and a 78% reduction in global public-policy staff.
The same report said median response time to user reports about posts had slowed by 20%, while median response time for reports concerning direct messages had slowed by 75%. See the eSafety Commissioner’s summary of X’s transparency response.
Those figures are stronger evidence than screenshots of bad posts. They describe a documented change in the resources available to operate the system.
The audience did not become small
X was still describing itself as a massive service after the cuts. In its October 2023 company update, X said more than half a billion people visited the platform each month and reported 7.8 billion active minutes per day. See X’s own one-year post-acquisition update.
That does not mean half a billion people needed human moderation every month. Automation, policy changes, user reporting, and systems such as Community Notes can change how much work requires a person.
X has explicitly argued that its moderation strategy evolved rather than simply disappeared. The company has emphasized Community Notes, automated enforcement, and new safety work in particular areas. It later reported major enforcement activity against child sexual exploitation and said it was building a trust-and-safety center in Austin.
So the useful claim is not X stopped moderating. The documented record does not support something that simple.
The useful claim is that a platform serving hundreds of millions of people substantially reduced several categories of specialized safety staff and experienced slower report response times during the same period.
Moderation is part of service quality
For ordinary users, moderation is usually invisible until it fails.
Spam stays up longer. Harassment reports sit unresolved. Appeals take longer. Coordinated abuse becomes harder to investigate. The visible symptom may look like a content problem, while the underlying problem is capacity.
That makes moderation investment comparable to server capacity or customer support staffing. A giant platform can remain technically online while reducing the human systems that make participation tolerable.
The audience size is therefore only half the measurement.
The other half is how much infrastructure the platform still commits to governing the audience it already won.