It's not enabled by default for their function calling API. So, hallucination is possible.

You have to set 'strict' to True manually to use the same grammar-based sampling they use for structured outputs.

https://platform.openai.com/docs/guides/function-calling?api...

Try this trick that I learned from Cohere: - Fetch top 10*k (i.e. 100) results using the hamming distance - Rerank by taking dot product between query embedding (full precision) and binary doc embeddings - Show top-10 results after re-ranking

This is pretty cool. The dot product would give the unnormalized cosine similarity from a smaller pool. Thank you so much!

OpenAI recommends using o1 to generate the verbose plan and then chain the verbose output to a cheaper model (e.g. gpt-4o-mini) to convert it into structured data / function calls / summary etc. They call it planner-executor pattern. [1]

[1] https://vimeo.com/showcase/11333741/video/1018737829

I've elaborated number 9. Please let me know if it's clear now.

Some of these methods do. For example, the tasks that power word vectors apply for many languages. https://fasttext.cc/docs/en/crawl-vectors.html

Masked Language Modeling has been applied to learn cross-lingual language models. Look into: https://arxiv.org/abs/1901.07291

Detecting sarcasm is a hard problem.

Even humans fails on this very often.

Haha, just imagine if an AI faces Chandler

Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)

https://www.aclweb.org/anthology/P19-1455

Great to know.

In my home country Nepal. Cheap cost of living and beautiful places to travel and explore.

1. Key ideas: I basically skim through blog posts and videos from conferences to be aware of key ideas in Machine Learning

2. Fundamentals: Parallelly, I take MOOC course every once in a while to learn fundamental concepts from first principles

3. Implementation: I either use the ideas I learned from (1) and (2) in a work project or write a blog post to make it concrete on my personal blog: https://amitness.com/

Twitter.

Working on a personal blog: https://amitness.com