Ian Fischer: How Stilts Beat a Frontier Model on ARC-AGI V2

Poetic's stilts pair self-improvement with an inference harness, not fine-tuning; it topped ARC-AGI V2 at lower cost than frontier deep-thinking modes.

Ian FischerguestJared FriedmanhostDiana Huhost

Feb 27, 202619mWatch on YouTube ↗

EPISODE INFO

Released: February 27, 2026
Duration: 19m
Channel: Y Combinator
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

Poetiq is a new startup founded by former DeepMind researchers that recently achieved a major jump on the ARC-AGI benchmark by layering a recursive self-improvement system on top of existing models. In this episode of Lightcone, Poetiq's Founder & CEO Ian Fischer joined us to discuss how small teams can build “reasoning harnesses” that outperform base models, what that means for startups and why automating prompt engineering may be one of the most powerful levers in AI today. Chapters: 00:00 – Intro 00:40 – What Is Poetiq? 01:07 – Recursive Self-Improvement Explained 02:07 – The Fine-Tuning Trap 02:59 – “Stilts” for LLMs 03:14 – Recursive Self-Improvement vs. Fine-Tuning 05:05 – Taking the Top Spot on ARC-AGI 06:37 – Beating Claude on Humanity’s Last Exam 08:40 – How the Meta-System Works 10:26 – Beyond RL: A New S-Curve 11:32 – Automating Prompt Engineering 13:37 – From 5% to 95% Performance 14:50 – Early Access & Putting Your Agent on Stilts 16:17 – From YC Founder to DeepMind Researcher 18:29 – Advice for Engineers in the AI Era Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs

SPEAKERS

Ian Fischer
guest
Jared Friedman
host
Diana Hu
host

EPISODE SUMMARY

In this episode of Y Combinator, featuring Ian Fischer and Jared Friedman, Ian Fischer: How Stilts Beat a Frontier Model on ARC-AGI V2 explores poetic’s seven-person team builds “stilts” that boost LLM reasoning Poetic (founded by ex-DeepMind researcher Ian Fischer) develops a “recursively self-improving” meta-system that generates task-specific reasoning harnesses—code, prompts, data, and multi-model routing—that sit on top of existing LLMs.

RELATED EPISODES