Artificial Intelligence

Firework CEO: Post-Training is Key to Unique AI Business

Firework CEO Lin Qiao discusses the strategic importance of post-training AI models to build unique business value and achieve competitive advantages.

StartupHub.ai Staff

By StartupHub.ai Staff, reviewed by Daniel Singer, Editor

3 min read

Lin Qiao, CEO of Firework, presenting on post-training AI models.
Credit: Sequoia Capital
Visual TL;DR
AI Dev Costs DropDriver
advancements in AI collapsing resource requirements for application development
Off-the-Shelf AIDriver
companies relying on generic APIs for their AI needs, lacking differentiation
From the articleQiao highlighted how the collapsing of resource requirements in application development, driven by advancements in AI, is shifting companies from relying on off-the-shelf APIs to building more deeply differentiated products.
Firework CEO QiaoCore
Lin Qiao emphasizes strategic importance of post-training AI models
From the article 2 mentionsIn a recent talk, Lin Qiao, CEO and co-founder of Firework, a specialized intelligence platform, emphasized the critical role of post-training in building durable AI-powered businesses.
Post-Training KeyContext
critical role of post-training in building durable AI-powered businesses
From the article 3 mentionsQiao also highlighted six common ways teams burn time and money in post-training:
Own IntelligenceEffect
From the article 6 mentionsAnd that means they carry their own judgment, taste, and determination, conviction into that product." Building on this, she believes that companies must bake their unique judgment and customer understanding into the intelligence they build, rather than relying solely on generic APIs.
Avoid PitfallsEffect
prevents common issues arising from generic, undifferentiated AI solutions
Unique Business ValueOutcome
achieve competitive advantages and solve unique problems in special ways
Real-World SuccessOutcome
demonstrates practical applications and benefits of this strategic approach
From the articleFinally, serving these models effectively, through A/B testing and iterative loops, is crucial for success.
Contents(4)

In a recent talk, Lin Qiao, CEO and co-founder of Firework, a specialized intelligence platform, emphasized the critical role of post-training in building durable AI-powered businesses. Qiao highlighted how the collapsing of resource requirements in application development, driven by advancements in AI, is shifting companies from relying on off-the-shelf APIs to building more deeply differentiated products.

Firework CEO: Post-Training is Key to Unique AI Business - Sequoia Capital
Firework CEO: Post-Training is Key to Unique AI Business, Sequoia Capital

Owning Intelligence, Not Renting

Qiao argued that in the current AI landscape, where open models are gaining traction, the depth of an alliance between companies stems from a shared belief in the industry's potential. She stated, "Every single company exists for a reason because they focus on solving a unique problem in a special way. And that means they carry their own judgment, taste, and determination, conviction into that product." Building on this, she believes that companies must bake their unique judgment and customer understanding into the intelligence they build, rather than relying solely on generic APIs.

Owning one's intelligence, according to Qiao, starts with data. This includes curating high-quality production data and generating synthetic data to enrich existing datasets. The next step involves using this data to build models and own the weights, employing a collection of techniques tailored to specific problems. Finally, serving these models effectively, through A/B testing and iterative loops, is crucial for success.

The Post-Training Progression

Qiao outlined a progression for AI development, starting with simple prompting, then moving to Retrieval Augmented Generation (RAG) to ground AI in a company's own data. This is followed by supervised fine-tuning (SFT) or LoRA for teaching format and behavior, preference tuning (like DPO) for personalizing taste and tone, and finally reinforcement learning (RL) for optimizing on a reward signal. She noted that while SFT transfers new knowledge, RL sharpens behavior, and that most teams eventually incorporate RL.

Avoiding Common Pitfalls

Qiao also highlighted six common ways teams burn time and money in post-training:

  • Data quantity over quality: Pristine examples are more valuable than noisy ones.
  • No eval before training: If you can't measure improvement, you can't ship it.
  • Sloppy RL environments: Imperfect training can lead to shortcuts that break in production.
  • Training-serving drift: Small gaps in compounds can lead to significant drift over time.
  • Wrong tool for the job: Fine-tuning is for facts, RL is for behavior.
  • Building the car vs. tuning the engine: Focus on data and reward signals first.

Real-World Successes

Qiao showcased several examples of companies successfully leveraging post-training on Fireworks' platform. Cursor, a coding assistant, has continuously released new models, competing at the frontier of quality. Doximity, a healthcare AI company, topped the Stanford-Harvard clinical safety benchmark. Factory, a security-focused company, tuned a model that excelled in risk detection.

These examples, Qiao emphasized, demonstrate that by focusing on custom data and leveraging open models, companies can build specialized intelligence that outperforms even closed frontier models in quality, cost, and speed.

Mentioned in this story

Get the free daily brief every morning

Every morning the day's AI news, new AI startups and new funding rounds. Free and takes a few minutes to read, unsubscribe at any time.

Join 64,000 other subscribers.

TopicsLin QiaoFireworkAIMachine LearningPost-TrainingReinforcement LearningSFTLoRA

StartupHub.ai Staff

Written by

StartupHub.ai StaffEditorial team

The staff writers of StartupHub.ai, ranging from investment analysts to avid AI tool users, early adopters and critical enthusiasts. Backgrounds span engineering, business and the arts. We hold every piece to rigorous standards of research and review.

Daniel Singer

Reviewed by

Daniel Singer is an AI expert who has been writing about, covering and building AI technology since 2018.

Test your Agent Readiness now

Paste your website. How well ChatGPT, Claude and the other agents can read and use a site, in about a minute.

Watch

The videos behind the news, one flip at a time

The feed mixes the videos from our articles with startup demos and you flip through them like TV channels for free with no signup.