OpenAI announced these API updates 3 days ago:
- new function calling capability in the Chat Completions API
- updated and more steerable versions of
gpt-4
andgpt-3.5-turbo
- new 16k context version of
gpt-3.5-turbo
(vs the standard 4k version) - 75% cost reduction on our state-of-the-art embeddings model
- 25% cost reduction on input tokens for
gpt-3.5-turbo
- announcing the deprecation timeline for the
gpt-3.5-turbo-0301
andgpt-4-0314
models
gpt-3.5-turbo
with the 16k context can now fit about 20 printed pages in its context. This is a game changer for summarization and documentation-based question answerint applications. I tried it in the API playground ant it works really well!Function calling also seems very useful for tool-using apps. No more crossing fingers and hoping the LLM will return a syntactically valid call!