Ask HN: What's up with the ChatGPT spam here lately?
A rise in ChatGPT-generated comments on a platform has been observed, with new low-karma accounts posting superficial content. Users seek methods to identify and block these accounts, considering dataset compilation for classifier training.
There has been a noticeable increase in comments likely generated by ChatGPT on a platform, characterized by accounts with low or negative karma that were created recently. These accounts have begun posting within the last week, often rephrasing the titles or content of posts and adding superficial questions. Users are seeking effective heuristics to identify and block these accounts, and there is a suggestion to compile a dataset to train a classifier for better detection. Concerns are raised that if this trend continues, manual moderation may not be sufficient to manage the influx of such comments.
Related
6 commentsBesides, how would the classifier scheme work? Validate the input or prune the threads? Good luck with either approach.
1. *Heuristic Identification*: - *Account Age and Karma*: As you mentioned, new accounts with low or negative karma could be a red flag. Filtering out comments from these accounts might help, although it might also block new, genuine users. - *Comment Content*: Look for patterns in the comments, such as generic or overly formal language, repetition, and lack of personal experience or detailed technical knowledge. - *Engagement Metrics*: Check the engagement these comments receive. Comments that are ignored or downvoted could be another indicator.
2. *Training a Classifier*: - *Data Collection*: You'd need a dataset of known AI-generated comments and genuine comments. This could be challenging but necessary for creating an effective classifier. - *Features*: Potential features for the classifier could include linguistic cues, metadata (account age, karma), and engagement metrics (upvotes, downvotes, replies). - *Community Involvement*: Encourage the community to flag suspected AI-generated comments. This could provide more data for training and improve the classifier's accuracy.
3. *Manual Moderation*: - While manual moderation might not be scalable, especially if the volume increases, it is still crucial for edge cases where automated methods might fail. - Moderators could focus on verifying flagged comments rather than monitoring all comments, making the process more efficient.
4. *Community Guidelines*: - Clear guidelines about AI-generated content could help. Encourage transparency if users are experimenting with AI-generated comments and provide a proper context.
5. *Technical Solutions*: - *CAPTCHA*: Implementing CAPTCHAs during account creation or before posting could deter automated systems from flooding the site. - *Rate Limiting*: Limiting the number of posts or comments a new account can make in a short period could reduce the impact of spam accounts.
By combining these approaches, HN can better manage the influx of AI-generated content and maintain the quality of discussions.