About this episode
We unpack the SSD (Speculative Speculative Decoding) approach to speculative decoding—precomputing multiple token paths while the giant model validates the first guesses. Learn how Saguaro, geometric fanout, and Saguaro sampling cut idle compute, enable up to 5x speedups on models like Llama 3 and Qan3, and why smart fallbacks keep the pipeline humming. Plus, explore the broader implications for self-optimizing systems and future AI hardware.
Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.
Sponsored by Embersilk LLC
Get every episode summarized
Each time Intellectually Curious publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Intellectually Curious
Free Pause Tokens Solve AI Multitasking
Intellectually Curious
Claude’s Autonomous Formalization of Fermat’s Last Theorem
Intellectually Curious
Random Attention: How AI Gets Faster by Forgetting
Intellectually Curious
The Alien Anatomy of the Bigfin Squid
Intellectually Curious