HN top 30 summarized by Gemini 2.5 Pro

It was quite interesting to vibe code this artifact. I learned some basic ideas about commitment scheme and hash cryptography in the half and hour spent on this. One of the few times vibe coding left me feeling enriched rather than drained. What do you think?

I was looking for some fun project to play around with the latest Gemini models and ended up building this :) Enter your username and get: - Generated roasts and stats based on your HN activity 2025 - Your personalized HN front page from 2035 (inspired by a recent Show HN [0]) - An xkcd-style comic of your HN persona It uses the latest gemini-3-flash and gemini-3-pro-image (nano banana pro) models, which deliver pretty impressive and funny results. A few examples: - dang: https://hn-wrapped.kadoa.com/dang - myself: https://hn-wrapped.kadoa.com/hubraumhugo Give…

Hey HN, I just updated my project that compares some LLMs. It uses your prompt for all the models and runs at the same time. You can see the results being generated in real-time and decide what's the best for your use case. I'm open to any suggestions and feedback. Thanks!

I was inspired by the notification summaries on iOS 18 and really liked the idea of AI giving you a quick preview of the content before going to the content. I applied that to HN and built a Chrome extension that summarizes the sentiment and content of HN comments and previews it right next to the stories on the homepage. Makes it so much easier to decide whether I want to delve into the HN comments of a story. It gave me a chance to play with Gemini 1.5 Flash-8B which has been great. Super fast, super cheap, huge context and does a great john on basic tasks like summarizing comment threads.…

Hey HN! Thank you for all the support and feedback on my original submission 2 months ago. I've been improving the backend using a MCTS/AlphaZero approach and it's currently producing much better results. My long term goal is to allow users to manage multiple projects, deployed autonomously, both from scratch and by making continual updates all prompted with natural language. The cost of each project has been lowered to $9 as performance with smaller models has improved (I migrated from Claude-3-Opus to gemini-1.5-flash). Thanks for checking it out!

I recently custom prompted 1.5 pro to teach me new words by helping me to make sentences using them - the only way to learn vocab IMO. It's been helpful for my GRE prep, hope you may find it useful as well!