HutHut
Fantasy football AI
What it does
I've played fantasy football for years with a system: read every piece of player news, track coaching and GM changes, listen to the fantasy podcasts, read the analyst articles, and synthesize all of it into draft and start/sit decisions. Then I became a dad, and the hours for it disappeared. So I built this app. HutHut presents the distilled research I would have done myself, I review it in minutes and decide, or ask the AI, which answers from machine learning projections so no emotions
HutHut is a fantasy football AI assistant for lineup, draft, waiver, and trade decisions, with an explanation for each recommendation.
HutHut answers lineup, draft, waiver, and trade questions. It evaluates the relevant factors and recommends what to do. Trades, sleepers, flex calls, draft picks. Prime gives a recommendation and shows the reasoning behind it. Every player carries a confidence grade built from matchup strength, snap and target trends, and breakout signals. A round-by-round target board for PPR, Half, Standard, and Superflex, showing who is a value against their ADP and who to fade. Waiver targets for any league. See who managers are adding, how heavily a player is being covered, and who is likely available at your league size. Player news as it breaks, with push alerts for injuries, inactives, and role…from huthuthike.ai
Does a similar job
all alternatives →- IBI build a Fantasy NHL app in 3 days with Claude AI2025 · ▲35
I am not from North America, and moved there a couple years ago. After being invited to the first fantasy league and seeing the platform they were using, I couldn't bring myself to check it every day. An excel sheet would have been more appealing to use than this. So I decided to create my own. But on the side? This would take ages. I am very confident with Rust and JavaScript, but it still takes ages to build something like that. Good prompts, and a few long nights later, and I could create something fun and easy to use. Have a look: https://fantasy-frontend.fly.dev/ The…
- IBI built a free AI service for fantasy sports2021 · winfantasy.ai · ▲12
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, September 2026
the whole month →
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
- OD
I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!
Life & fun · 5d ago · github.com
Turn text, pics, video, + 3D into camera-controlled HD video
AI · 5d ago · worldlabs.ai