New models and developer products announced at DevDay

We went to OpenAI's office in San Francisco yesterday to ask them all the questions we had on Quivr (YC W24), here is what we learned:

1. Their office is super nice & you can eat damn good croissant in SF!

2. We can expect GPT 3.5 & 4 price to keep going down

3. A lot of people are using the Assistants API to build their use cases

4. It costs ... See more

To do this, we employ a technique known as AI-assisted evaluation, alongside traditional metrics for measuring performance. This helps us pick the prompts that lead to better quality outputs, making the end product more appealing to users. AI-assisted evaluation uses best-in-class LLMs (like GPT-4) to automatically critique how well the AI's output... See more