We are pleased to share our latest research, now published in Nature Communications: “Smart Cellular Bricks: Physical Modules That Recognize Their Own Shape and Repair Themselves.” Blog: sakana.ai/smart-cellul... Paper: www.nature.com/articles/s41... Thread 🧵
Smart cellular bricks for decentralized shape classification and damage recovery | Nature Communications nature.com
AI Weekly's analysis
→
- Cubic bricks running identical neural cellular automata policies classified four 3D shapes with 98.97% accuracy in simulation and 100% on physical hardware.
- Physical builds ranged from 26 bricks for a guitar to 197 for a round table, converging on a shape label in fewer than 60 update cycles.
- The same decentralized framework detects structural damage with over 90% accuracy and guides regrowth by predicting one of six axis directions.
Read full analysis →
View on Bluesky ·
♥ 51
↻ 6
↩ 2
·
3 from the directory shared this ·
57d ago
全文： microsoft.com/en-us/corpor... 🐟
Open Weights and American AI Leadership microsoft.com
The AI Picbreeder Experiment: Can AI agents be creative when nobody tells them what to create? Blog: pub.sakana.ai/picbreeder-vlm Paper: arxiv.org/abs/2605.23908 In our #GECCO2026 paper, we revisit Picbreeder, a website where people collaboratively evolved images without any p…
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models arxiv.org
AI Weekly's analysis
→
- Researchers Sam Earle, Kai Arulkumaran, Andrew Dai, Akarsh Kumar, Julian Togelius and Sebastian Risi replicate Picbreeder with frontier vision-language models as users.
- The system's output shows 'clear qualitative differences' from the historical human baseline on phylogenetic complexity and visual and semantic salience and novelty.
- The team studies three candidate ingredients: exploratory noise in selection, behavioral diversity between agents, and memory-based narrative momentum.
Read full analysis →
View on Bluesky ·
♥ 20
↻ 1
↩ 1
·
2 from the directory shared this ·
60d ago
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks. Read the full blog: sakana.ai/fugu-release Beyond Bigger Models: Why are Orchestration Models the Next Frontier (Th…
Sakana AI sakana.ai
View on Bluesky ·
♥ 21
↻ 2
↩ 1
·
6 from the directory shared this ·
78d ago
Fugu-Ultra is now live on OpenRouter! ⚡ We share a core vision with the OpenRouter team: the future of AI isn’t a single monolithic model, but the collective intelligence of the world’s best models working together. Try it: openrouter.ai/sakana/fugu-... 🐡
Fugu Ultra - API Pricing & Providers openrouter.ai
AI Weekly's analysis
→
Read full analysis →
View on Bluesky ·
♥ 28
↻ 2
↩ 1
·
4 from the directory shared this ·
76d ago
Sakana Chat just got an upgrade. Powered by Fugu and Namazu, our Japanese LLM. With newly added code execution, you can vibe-code interactive web apps, games, and tools in seconds by describing them (even in Japanese). No login required, free to use: chat.sakana.ai 🐟
Sakana Chat chat.sakana.ai
AI Weekly's analysis
→
Read full analysis →
View on Bluesky ·
♥ 22
↻ 4
↩ 2
·
3 from the directory shared this ·
26d ago
Can a general-purpose vision model tell real from AI-generated images with just a simple decision rule on frozen features? Our #ECCV2026 paper says yes. Blog: pub.sakana.ai/percept-lens/ Paper: arxiv.org/abs/2608.18523
Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection arxiv.org
We are pleased to share our latest research, now published in Nature Communications: “Smart Cellular Bricks: Physical Modules That Recognize Their Own Shape and Repair Themselves.” Blog: sakana.ai/smart-cellul... Paper: www.nature.com/articles/s41... Thread 🧵
Smart Cellular Bricks: Towards Collective Intelligence for the Physical World sakana.ai
AI Weekly's analysis
→
- IT University of Copenhagen, Sakana AI, and Autodesk built cubic bricks that classify their own assembled 3D shape using only neighbor-to-neighbor communication.
- In simulation the system hit 98.97% accuracy across 500+ bricks; four physical objects (26 to 197 bricks) all reached correct consensus in under 60 cycles.
- The same Neural Cellular Automata substrate detects local damage at 94.8% average accuracy, with some shapes degrading only minimally at 15% brick failure.
Read full analysis →
View on Bluesky ·
♥ 51
↻ 6
↩ 2
·
3 from the directory shared this ·
57d ago
The AI Picbreeder Experiment: Can AI agents be creative when nobody tells them what to create? Blog: pub.sakana.ai/picbreeder-vlm Paper: arxiv.org/abs/2605.23908 In our #GECCO2026 paper, we revisit Picbreeder, a website where people collaboratively evolved images without any p…
The AI Picbreeder Experiment: In Search of Automatic Open-Endedness pub.sakana.ai
AI Weekly's analysis
→
- Researchers from NYU, MIT and Sakana AI replaced Picbreeder's human selectors with frontier VLMs and reported clear qualitative gaps versus the historical human baseline.
- Gemini-2.5-pro topped the models tested, but archives showed 'mode collapse' without exploratory noise and 'auto-sycophantic' loops when given more history.
- Scaling to 1,000 agents widened coverage yet 10 to 20 percent of the archive turned into uninterpretable adversarial psychedelic patterns.
Read full analysis →
View on Bluesky ·
♥ 20
↻ 1
↩ 1
·
3 from the directory shared this ·
60d ago
Introducing Fugu-Cyber: an update to our Fugu orchestration model. It achieves state-of-the-art performance on real-world security benchmarks, matching cyber-focused frontier models like GPT-5.5-Cyber and Mythos Preview. Release Blog: sakana.ai/fugu-cyber-r... 🐡
Sakana AI sakana.ai
AI Weekly's analysis
→
Read full analysis →
View on Bluesky ·
♥ 61
↻ 2
↩ 2
·
3 from the directory shared this ·
49d ago
Announcing Fugu-Ultra v1.1 🐡 We’ve been thrilled by the reception to the Fugu model family. Thanks to everyone who tried it, shared feedback, and trusted Fugu with real work. Today, we’re releasing Fugu-Ultra v1.1 → sakana.ai/fugu Upgraded to incorporate the latest frontier mo…
Sakana Fugu — Multi-agent System as A Model sakana.ai
AI Weekly's analysis
→
- Fugu routes tasks through a dynamic multi-agent pipeline exposed as a single OpenAI-compatible API, removing orchestration setup from users.
- The system draws on two ICLR 2026 papers: TRINITY assigns Thinker/Worker/Verifier roles; Conductor uses reinforcement learning to design coordination strategies.
- Fugu Ultra scored 73.7 on SWE Bench Pro and 93.2 on LiveCodeBench; base Fugu reached 95.5 on GPQA-D, per Sakana's own benchmark reporting.
Read full analysis →
View on Bluesky ·
♥ 57
↻ 3
↩ 1
·
2 from the directory shared this ·
46d ago
The next frontier of Recursive Self-Improvement is Physical AI. Japan sparked the robotics revolution. We’re expanding our RSI Lab to build world models that allow agentic reasoning systems to recursively self-improve their ability to simulate, plan, and act in the real world.…
Sakana AI sakana.ai
AI Weekly's analysis
→
- Sakana AI is hiring a Member of Technical Staff for its Tokyo-based Recursive Self-Improvement (RSI) Lab, targeting researchers frustrated with brute-force scaling.
- The role spans four tracks including world models as verifiable simulators for agentic reasoning and open-ended evolutionary dynamics applied to algorithmic domains.
- Sakana points to prior work as receipts: Darwin Gödel Machine on SWE-bench, ALE-Agent winning AtCoder Heuristic Contest 058, ShinkaEvolve with 150 samples.
Read full analysis →
View on Bluesky ·
♥ 33
↻ 2
↩ 0
·
2 from the directory shared this ·
25d ago
