OpenClaw founder uses AI scheduled task to clean up Twitter, specifically setting up cryptocurrency-related muting rules

According to 1M AI News monitoring, OpenClaw founder Peter Steinberger tweeted that he built a Twitter mention automatic block system using OpenClaw, running every 5 minutes, with results "better than expected." He receives a daily block summary email (Daily X Block Digest) listing the blocked accounts and the AI's judgment reasons. Within a recent 24-hour window, the system blocked 56 accounts.

Publicly disclosed blocked features in the summary email include:

1. Alt accounts posting generic praise generated by AI under unrelated posts
2. Cryptocurrency project accounts posting low-quality comments, with a history of token promotion tendencies
3. Image-only spam replies, recently active in staking/shill content
4. Conspiracy-theory-style lengthy accusation spam across posts, low signal-to-noise ratio
5. Directly leveraging celebrity traffic in replies to promote their own product
6. Hollow comments from degen/crypto type accounts

One user directly asked "Is this blocking reply guys (users who habitually hijack celebrity tweets for exposure)?" to which Steinberger answered "yes."

Regarding false positives, Steinberger said he evaluates each one when someone emails to appeal, but "usually it's indeed bad behavior, and the AI judgment is correct." He also added that merely using AI to assist in writing will not trigger a block, "as long as the content itself is meaningful," but doing so "will make you less popular."