Ricursive Intelligence is betting on AI-designed chips to help solve the compute crisis
Ricursive Intelligence says recursive AI chip design can ease a projected 10,000x compute-demand surge.
Ricursive Intelligence founders Anna Goldie and Azalia Mirhoseini told TechCrunch Disrupt that AI which designs chips, learns from each iteration, and optimizes entire layouts could ease a projected surge in compute demand. They cited AlphaChip, which produced an unconventional circular component arrangement that outperformed traditional partitioned designs. Goldie said designing a chip in about a week could make custom chips for space, AR, VR, and biological computing financially practical.
- Founders Anna Goldie and Azalia Mirhoseini spoke at TechCrunch Disrupt.
- They expect at least 10,000x more compute demand within five years.
- Their AI iterates full-chip layouts, including AlphaChip’s donut-shaped placement.
- Faster design could enable custom chips for space, AR, VR, and biology.
- Organizations
- Ricursive Intelligence
- AI models
- AlphaChip
From the original article
2 min read at techcrunch.com
The founders detailed how their startup is developing AI that can design chips, learn from each iteration, and improve subsequent designs, all with the goal of automating and accelerating the chip design process.
By Aisha Malik · techcrunch.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.