9&4 Caddie
Your digital caddie on the course. AI-powered club selection
What it does
Every amateur golfer faces the same problem: no caddie. You're 155m out, slight wind, rough lie — and you're guessing. Set up your bag, then on the course: enter distance, lie, and wind. Your caddie recommends the right club. What makes it different: → Personalised to your actual bag. → Adjusts for wind (+8m into, -5m with) and lie (rough, bunker) → Shot feedback loop — log Perfect / Short / Long / Offline after every shot Currently in beta. Free to use. Would love feedback from golfers.
Does a similar job
all alternatives →- IMI made a voice activated golf bag that shoots your clubs2021 · youtube.com · ▲142
- Pars in Progress AI Golf CoachJun 2026 · golfcoach-ai-gold.vercel.app · ▲2
Get instant golf coaching, drills, and practice plans
- IDIn-depth photographic look at all the golf courses I play2022 · golfscout.net · ▲18
I'm an avid golfer; it's my main hobby. I decided to start taking pictures of all the courses I play. While there's a lot of golf websites out there, none of them really try to document the courses in depth and look at each hole, along with the course facilities like the practice areas. I live in Chicago and am starting with the courses in this area (of which there are dozens of public courses to play). While I play golf, I take photos with my phone of every (relevant) aspect of the golf course I can think of. Then they're processed and organized on the website. Obviously I'm starting this…
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 · 19d 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