Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-02-24 · source-backed
poetiq.ai — Detailed technical breakdown of how a $40K-hardware startup achieved 54% on ARC-AGI-2 (vs. Google's 45% at nearly 3x the cost). The key innovation: "learned test-time reasoning" — an iterative refinement meta-system where solutions are generated, receive structured feedback, and self-improve through multiple loops. Crucially, this is LLM-agnostic and works across OpenAI, Anthropic, and xAI models. The meta-system IS the intelligence, not the underlying model. Symbolica's parallel work (85.28% with recursive delegation) confirms the pattern independently.
Each link below shares sources, entities, or timing with this story.
The ARC-AGI-2 breakthroughs reveal a concrete architectural pattern. Symbolica's Agentica achieves 85.28% (with Opus 4.6) using recursive delegation where sub-agents spawn sub-agents, each receiving only relevant state and avoiding context rot. Average 2.6 agents per task, max...
Poetiq (6-person ex-DeepMind startup) hit 54% on ARC-AGI-2 at $30.57/task, beating Google's Gemini 3 Deep Think (45%, $77.16/task) through iterative refinement loops — no fine-tuning required. Meanwhile, Symbolica's Agentica reached 85.28% using recursive sub-agent delegation...
GPT-5.4 scores 0.26%. Opus 4.6 scores 0.25%. Grok-4.20 scores 0.00%. Humans score 100%. The Decoder covered the ARC-AGI-3 launch on March 25, and the results make every "AGI is here" claim look premature. François Chollet launched ARC-AGI-3 at Y Combinator HQ alongside a fires...
CNN reports all five frontier labs (adding Google, Microsoft, and xAI to existing OpenAI and Anthropic agreements) now let the Commerce Department's Center for AI Standards and Innovation review models before public release. The agreement is voluntary, but normalization of gov...
GLM-5.1 from Zhipu AI scored 58.4% on SWE-bench Pro. GPT-5.4 scored 57.7%. Claude Opus 4.6 scored 57.3%. That's the first time an open-weight model has ever topped a major coding benchmark against the best proprietary models. The specs matter. GLM-5.1 is a 754B-parameter mixtu...
The ARC Prize Foundation dropped ARC-AGI-3 on March 25 and the results broke my mental model of how AI capability scales. Symbolica's Arcgentica framework scored 36.08% (113 of 182 playable levels, 7 of 25 games completed) using Claude Opus 4.6 as its backbone. Cost: $1,005. F...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.