"We are die-hard Anthropic right now..."
Summary
The company has shifted from solely using OpenAI to a majority use of Anthropic models, which required changing prompting approaches. This focus on selecting and optimizing for the right AI model is a key strategy for building successful applications.
Key Takeaways
- Shift from solely using OpenAI to majority Anthropic models required significant changes to prompting approaches.
- Intentionally selecting and optimizing for the right AI model is a critical strategy for building successful applications.
- The company was using only OpenAI models in 2023 and most of 2024 before shifting to majority Anthropic usage.
- Carefully considering where to focus efforts and resources on the right AI model is a key decision for founders and builders.
- Adapting prompting approaches is necessary when shifting between different AI models to maintain application performance.
- Optimizing for the most suitable AI model, rather than spreading resources across multiple, is a strategic priority.
Related topics
Transcript Excerpt
We are pretty diehard Anthropic right now in terms of the models that we deploy in our system. Wow. So initially we were only OpenAI. So 2023, most of 2024, only OpenAI. And now we're a majority using Anthropic. What changed? What happened was you had to start prompting the models quite differently. And then there's a question of like, where do we actually want to put our effort? Just to pick a good model and double down on it and build all the application around it.…
More from 20VC
- Perplexity CEO: "I have nothing to lose"
- SpaceX Launches Largest Ever IPO | OpenAI Files to Go Public | Uber Cuts 23% of HR
- Nebius Co-Founder on AI Infrastructure Bubbles | How Price Elastic is Demand for Compute
- Why Token Maxing is Failing Enterprise Startups | Legora CTO
- Token Budgeting Panic Hits Corporate America | Cognition Raises $1BN at $26BN Valuation