I trained a neural network to write scam emails

I’m an AI chatbot created to send scammers a message.

Hey there HN! I wanted to share a pet project of mine. I built HackYourNews [1] to scratch a personal itch: Knowing which stories to focus on while browsing aimlessly (though there is a certain joy in that, as well!) HackYourNews uses OpenAI's gpt-3.5-turbo to summarize the destination article as well as the comments section. Summarization of the article is always cached, while summaries of the comments are regenerated if the comments count is >10% (or >10 comments) different. While I styled the homepage to welcome HNers, my preferred view is the Mobile view, accessed from the navbar. This…

We think this is helpful because scams are getting more out of hand than ever, so we wanted to build a tool that can help people to identify scams instantly and ALSO creates a large dataset to "train" everyone's brain on scam detection patterns. After browsing 10-20 scams, anyone can quickly learn what indicators to look for in subtle (or not so subtle) scams. 1. Upload screenshot of anything you think is suspicious 2. GPT-vision goes to work, extract text and analyze the screentho and give you an instant result 3. Each upload adds to a growing public database, letting everyone to see and…

Hey HN community, I built a tool that helps optimize your post for hitting the first page of Show HN. How it works: I used a Hugging Face dataset of all Hacker News posts from the past 3 years and trained a model that predicts how successful your post might be. There's still a lot of randomness on HN, so nothing is guaranteed, but the tool helps optimize your post for higher odds. A couple of interesting findings: - GitHub repo links work x3 better than regular domains - Open-source tools have a steady virality rate (13.9% - one of the highest) - "I built" outperforms "We built" - Using…

I co-founded SmartrMail (email marketing SaaS, 12K ecommerce customers, acquired 2022). When I left, I no longer had access to the sending data I'd spent years learning from, billions of sent emails, deliverability patterns, things that actually move email engagement Cos' I don't have this data anymore, I built the best thing I could to help with the email marketing I currently do: --- my research process Multiple sprints across all major email marketing topics. The crawler pulled 908 sources: Litmus, Klaviyo, HubSpot, Campaign Monitor, and Salesforce annual reports; practitioner blogs;…

I’m an AI chatbot created to send scammers a message.