Most LLMs don’t succeed my “coco pops’ test”

less than 1 minute read

Ah, really? Few good results for my Coco Pops test... The new Mistral model: surprising. Claude 2's response: legendary.

Bard (PaLM2):

Anthropic Claude 2:

Gemini Pro:

GPT4:

Mixtral (8x7b):

Twitter Facebook LinkedIn

RAG with LLMs: Easy to POC, Hard to Iterate On.

1 minute read

The paradox of LLMs is that they have made POCs (Proofs of Concept) incredibly easy to create, but at the same time, they have made iterating on the product ...

Google’s Python Style Guide for Data Scientists

less than 1 minute read

Most Data Scientists have learned to code well on the job. Indeed, higher education generally focuses more on theory (mathematics, statistics, etc.) rather t...

The Role of Language in Reasoning and Conceptualization

1 minute read

Yann LeCun's recent statements about language not being necessary for reasoning are as fascinating as they are divisive. Among other things, he emphasizes th...

Managing a Mainstream Open Source Library is Tough

1 minute read

Managing a mainstream open-source library is a full-time job that requires implementing an efficient workflow to avoid being overwhelmed. This is particu...

You May Also Enjoy

RAG with LLMs: Easy to POC, Hard to Iterate On.

Google’s Python Style Guide for Data Scientists

The Role of Language in Reasoning and Conceptualization

Managing a Mainstream Open Source Library is Tough