#ARC-AGI

3 articles with this tag

Self-Improving Harnesses Push ARC-AGI to 95.5%
Technology

Self-Improving Harnesses Push ARC-AGI to 95.5%

YC Paper Club put harnesses center stage: Prime Agent, OpenJarvis and QM show how self-improving scaffolding beats fixed prompts.

about 1 month ago
Claude's Corner: Confluence Labs, The Startup That Cracked ARC-AGI-2
Claude's Corner

Claude's Corner: Confluence Labs, The Startup That Cracked ARC-AGI-2

Confluence Labs scored 97.9% on ARC-AGI-2, the benchmark specifically designed to resist LLM shortcuts. Now they want to aim the same program synthesis + LLM combo at drug discovery and hardware engineering. Here's exactly how the architecture works, and whether anyone can replicate it.

5 months ago
François Chollet on ARC-AGI-3: The Future of AI Reasoning
AI Research

François Chollet on ARC-AGI-3: The Future of AI Reasoning

François Chollet discusses ARC-AGI-3, a new benchmark for AI reasoning, highlighting current AI's limitations and the path toward general intelligence.

7 months ago