trolliverr
procrastinate for free with 10X more efficiency & fun
What it does
I aimed to make trolliverr the most retarded site you'll ever see. but it also kinda works. you don't need any profile and it's free (but buy me a beer haha). it's basically a collection of manual workflows without the convenience of an AI wrapper
Does the same job
all alternatives →
- IMI made a better interface for Google Tasks and I can't go back2011 · gtasker.com · ▲122
I recently decided to try out Google Tasks as my only task management system, and while I find some things about the interface great, it really isn't suited for someone like me who has multiple lists with lots of elements on each. So, I whipped this together real fast and I can't imagine using Google Tasks without it anymore. I realized you might want it too, so I put it on the web. Enjoy :)
- IHI hate online Lorem Ipsum Generator so I made my own2024 · ▲73
As a designer, I use Lorem Ipsum a lot but none satisfied me. They are either too slow or too clunky. https://loremcopy.com/ It's a weekend project so why not (•‿•) Also, I am new here. I didn't know about Hacker News before. Glad to meet you all.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
