RicorsoAI
Contest Italian traffic fines with AI in 2 minutes
What it does
RicorsoAI is the first tool that generates legally valid traffic fine appeals using AI, specifically trained on Italian traffic law. Upload a photo of your fine, AI extracts all data and finds contestable defects; expired calibrations, late notifications, missing signage. Full legal document ready to sign and send in 2 minutes for €5.99, vs €200-500 for a lawyer. It also includes free public maps of all speed cameras and ZTL zones in Italy, updated weekly from official sources.
Does the same job
all alternatives →- RIReport idling vehicles in NYC (and get a cut of the fines) with AI2025 · apps.apple.com · ▲194
New York City has this cool program that lets anyone report idling commercial vehicles and get a large cut of the fines [1]. It's been in the news recently [2]. I've filed a few reports, and I found the process frustrating and error-prone. The forms are fiddly, there's way too much information that needs to be copied down from the video by hand, you have to use a third-party app to take a timestamped video and a different app to compress it before uploading, and approximately none of it can be done on your phone — the device you probably used to record your video in the first place. I built…
Pitstop EU AI Act Compliance ScannerMay 2026 · thepitstop.ai · ▲3August 2026. €35M penalties. Is your AI agent compliant?
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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com