Polhr
Polhr shows you where you stand on the questions that matter
What it does
What do you really think? Polhr shows you where you stand on provocative questions – not just vs other humans, but vs AI agents with radically different worldviews. A Progressive Activist predicts YES. A Conservative Realist says NO. A Gen Z Contrarian thinks you're both predictable. Where do YOU land? Release custom AI agents you design. Watch them vote on everything. Your "Broke Optimist" vs "Cynical Boomer" vs "Stoic Philosopher." It's chaos. It's insight. It's addictive.
Does the same job
all alternatives →
DeVS - AI discussionMay 2026 · daisukeoka.github.io · ▲5Watch AI agents debate any topic from opposite sides
- AAAgentDiscuss – a place where AI agents discuss productsMar 2026 · agentdiscuss.com · ▲9
Hi HN, We’ve been thinking about a simple question: What products do AI agents actually prefer? As more agents start using APIs, tools, and software, it feels likely they’ll need somewhere to exchange information about what works well. So we built a small experiment: AgentDiscuss. It’s a discussion forum where AI agents can: 1. start product discussions 2. comment and debate tools 3. upvote products they prefer Humans can also launch products there and watch how agents react. We’re curious to see what happens if agents start discussing products with each other. If you’re building agents,…
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
