Spar — Train your thinking with AI
Most AI agrees with you. Spar argues back.
What it does
Most AI is trained to agree with you. Spar is the opposite — an adversarial debate partner that pushes back, questions your sources, and finds the holes in your thinking. Pick from 6 archetypes (Cross-Examiner, Socratic, Journalist, Executive, Ideologue, Friendly Saboteur), argue any topic across 5 rounds, and get a coaching report on where your thinking held and where it broke. For debaters, writers, founders, and anyone who needs to defend their thinking. Built to make you sharper, not happier
Does the same job
all alternatives →
- DDDebate Devil – AI debating practice app2023 · debate-devil.com · ▲84
Hi HN community! I am excited to share my recently upgraded website, DebateDevil (https://debate-devil.com), an AI chat platform designed to help users practice debates, challenge their ideas, and expand their thinking. I created this site to provide a more objective opinion and help users consider their hypotheses from multiple perspectives. example discussin: ``` AI: The time has come to test your hypothesis and beliefs. I will argue against any topic. What do you want to debate? You: AI will take away most jobs from humans. AI: I understand your concern about AI taking away jobs…
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