Fireworks AI

4 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Mar 27, 2025 by Lin Qiao · said 26 times in 5 episodes since 2024 · across every show →

Mentions by year

brought up most by Matt Turck (17), Lin Qiao (5), Ivan Borzin (2), Thomas Wolf (1), Erik Bernhardsson (1)

mentionsepisodesper episode tap a year for its mentions

2026 4 mentions in 3 episodes 1 per episode

The Agent Harness: Building Secure Sandboxes for Autonomous AI Workloads May 14, 2026 · 2 mentions · from 54:35
“OpenAI’s Model Hacked Us” - Hugging Face’s Thomas Wolf Aug 6, 2026 · 1 mention · from 35:35
Cerebras CEO: Why GPUs Can't Do Fast Inference Jul 23, 2026 · 1 mention · from 59:58
every mention in 2026, scene by scene →

2025 21 mentions in 1 episode

Why This Ex-Meta Leader is Rethinking AI Infrastructure | Lin Qiao, CEO, Fireworks AI Mar 27, 2025 · 21 mentions · from 0:04
every mention in 2025, scene by scene →

2024 1 mention in 1 episode

Can AI Infrastructure Work Like Magic? Erik Bernhardsson, CEO, Modal Oct 31, 2024 · 1 mention · from 5:55
every mention in 2024, scene by scene →

every mention, scene by scene, with the transcript →

Everything said about Fireworks AI, oldest first

Mar 27, 2025

Assertion Contradicted

Fireworks AI was first to enable function calling for DeepSeek models

“We have been working on function for calling for a long time, and we are the first one to enable function calling for deep seek models.”

Lin Qiao Mar 27, 2025 ▶ 43:58 Why This Ex-Meta Leader is Rethinking AI Infrastructure | Lin Qiao, CEO, Fireworks AI

Mar 27, 2025

Assertion Not checkable as stated

Lin Qiao: Fireworks AI's optimization space has over 80,000 options

“And all these different options add up together, it can lead into more than 80,000 possible, possible way to optimize.”

Lin Qiao Mar 27, 2025 ▶ 32:38 Why This Ex-Meta Leader is Rethinking AI Infrastructure | Lin Qiao, CEO, Fireworks AI

Mar 27, 2025 positive

Assertion Not checkable as stated

Fireworks AI improved speculative execution hit rates from 30% to 90%

“We have seen cases improving the prediction hit from 30% to 90%, and that's huge speed.”

Lin Qiao Mar 27, 2025 ▶ 29:25 Why This Ex-Meta Leader is Rethinking AI Infrastructure | Lin Qiao, CEO, Fireworks AI

May 14, 2026

Assertion Partly supported

Borzin: Base10 and Fireworks AI run on over a dozen compute providers

“Both of them run on more than a dozen compute providers, depending on what you want to call them.”

Ivan Borzin May 14, 2026 ▶ 55:06 The Agent Harness: Building Secure Sandboxes for Autonomous AI Workloads

Fireworks AI

Mentions by year

Everything said about Fireworks AI, oldest first

Turn any episode into a week of clips.