Skip to content
YC Root AccessYC Root Access

This Startup Beat Gemini 3 on ARC-AGI — at Half the Cost

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 Gemini 3. In this conversation at NeurIPS, YC's Francois Chaubaurd sat down with Poetiq co-founder Ian Fisher to find out how they're increasing performance using prompts and system design alone. They also explore recursive self-improvement, benchmarking progress toward AGI, and why automating prompt engineering may be one of the most powerful levers in AI today. Chapters 00:11 — Introducing Poetiq and the ARC-AGI Breakthrough 00:49 — How Big Is the Performance Jump? 01:18 — Ian Fisher’s Background: YC, Google, DeepMind 02:00 — Recursive Self-Improvement Explained 03:00 — Why Poetiq Targeted ARC-AGI 03:58 — Improving Models Without Access to Weights 04:26 — Ensembles, Voting, and System-Level Optimization 05:30 — Why Gemini 3 Changed Everything 06:21 — What’s Next: Benchmarks, Research, and Customers 07:14 — Is Recursive Self-Improvement a Path to AGI? 08:46 — When to Stop Hill-Climbing 09:16 — Automating Prompt Engineers and Agents

Francois ChaubaurdhostIan Fisherguest
Jan 29, 202611mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
January 29, 2026
Duration
11m
Channel
YC Root Access
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 Gemini 3. In this conversation at NeurIPS, YC's Francois Chaubaurd sat down with Poetiq co-founder Ian Fisher to find out how they're increasing performance using prompts and system design alone. They also explore recursive self-improvement, benchmarking progress toward AGI, and why automating prompt engineering may be one of the most powerful levers in AI today. Chapters 00:11 — Introducing Poetiq and the ARC-AGI Breakthrough 00:49 — How Big Is the Performance Jump? 01:18 — Ian Fisher’s Background: YC, Google, DeepMind 02:00 — Recursive Self-Improvement Explained 03:00 — Why Poetiq Targeted ARC-AGI 03:58 — Improving Models Without Access to Weights 04:26 — Ensembles, Voting, and System-Level Optimization 05:30 — Why Gemini 3 Changed Everything 06:21 — What’s Next: Benchmarks, Research, and Customers 07:14 — Is Recursive Self-Improvement a Path to AGI? 08:46 — When to Stop Hill-Climbing 09:16 — Automating Prompt Engineers and Agents

SPEAKERS

  • Francois Chaubaurd

    host

    Visiting partner at Y Combinator and host of YC Root Access interviews.

  • Ian Fisher

    guest

    Co-founder and co-CEO of Poetic, discussing their ARC-AGI results and model-evaluation approach.

EPISODE SUMMARY

In this episode of YC Root Access, featuring Francois Chaubaurd and Ian Fisher, This Startup Beat Gemini 3 on ARC-AGI — at Half the Cost explores poetic boosts Gemini 3 ARC-AGI scores via recursive optimization Poetic reports 54% on the ARC-AGI 2 private test set by running its system on top of Gemini 3, exceeding Gemini 3 DeepThink’s ~45% while costing about half as much.

RELATED EPISODES

Senator Scott Wiener Press Conference at YC

Senator Scott Wiener Press Conference at YC

How to Build an Internal AI Agent That Evolves Itself

How to Build an Internal AI Agent That Evolves Itself

How to Give AI Agents Enough Context to Be Useful

How to Give AI Agents Enough Context to Be Useful

Circle CEO: 3 Things That Will Transform Stablecoins in 2027

Circle CEO: 3 Things That Will Transform Stablecoins in 2027

This $1.5 Trillion Industry Still Runs on Paper and Fax Machines

This $1.5 Trillion Industry Still Runs on Paper and Fax Machines

The Tool the Best Engineers Are Using Right Now

The Tool the Best Engineers Are Using Right Now

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.