ATLAS

What it does

ATLAS is grounded in the 2026 Google DeepMind paper "Measuring Progress Toward AGI: A Cognitive Framework" (Burnell et al.), which identifies Learning as one of 10 core cognitive faculties and decomposes it into six sub-types. Where most benchmarks test knowledge retrieved from training data, ATLAS uses procedurally generated interactive environments where the model must discover hidden rules through trial-and-error in real time. No answer can be looked up. Every game is a new learning problem.

• 
  Atlas.newJan 2026 · ▲525

  The AI agent for maps and spatial data

• 
  Foundations Atlas2019 · ▲96

  ML dev tool that saves you up to 8x in cloud GPU costs

• 
  Undermind Atlas2018 · ▲85

  An open-source teacherbot

• 
  Knowledge Atlas by FiniJul 2026 · usefini.com · ▲104

  The self-learning knowledge base that improves itself

• PG
  Predict GPT-5 skills with a community AI benchmark2025 · ▲13

  I’m Andrew, co-founder of Recall. Over the past few days I’ve been building Predict, a playground where anyone can: - propose skills we should measure in language models—live examples include difficult math, memory-manipulation resistance, code generation, and empathy under bad news - write evals (graded prompts) for those skills - forecast which models will score highest once GPT-5 is released Why this exists Benchmarks leak into training data quickly; scores are unreliable and labs still declare progress. The prediction tool aims keeps the target moving by letting the crowd define both the…

• CB
  Cua-Bench – a benchmark for AI agents in GUI environmentsJan 2026 · github.com · ▲40

  Hey HN, we're excited to share Cua-Bench ( https://github.com/trycua/cua ), an open-source framework for evaluating and training computer-use agents across different environments. Computer-use agents show massive performance variance across different UIs—an agent with 90% success on Windows 11 might drop to 9% on Windows XP for the same task. The problem is OS themes, browser versions, and UI variations that existing benchmarks don't capture. The existing benchmarks (OSWorld, Windows Agent Arena, AndroidWorld) were great but operated in silos—different harnesses,…

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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

• 
  Monid▲474

  OpenRouter for agent tools

  AI · 6d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 19d ago · clarasdr.ai

• 
  Brew ▲905

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲897

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲805

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲796

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• NW
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  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
  Files.md – Open-source alternative to Obsidian▲730

  Dev tools · May 2026 · github.com