Discussion w Arthur Mensch, CEO of Mistral AI
Mistral launched multiple LLM models in less then 1 year from founding. We discuss
Elad Gil Blog30 min read
retrieval augmented generation
529 stories
Do text embeddings perfectly encode text?
'Vec2text' can serve as a solution for accurately reverting embeddings back into text, thus highlighting the urgent need for revisiting security protocols around embedded data.
The Gradient9 min readTrue Zero-shot MT
Little over a week ago, Gemini 1.5 reported close to human-level performance on MTOB, a recent challenging translation dataset. In this newsletter, we’ll dig into this result, explore true zero-shot machine translation (MT), and consider how to teach LLMs a new language like humans.
NLP News (Sebastian Ruder)10 min readThings I Don't Know About AI
The more I learn about AI markets, the less I think I know. I list questions and some thoughts.
Elad Gil Blog12 min readHow to Structure JSON Responses in ChatGPT with Function Calling
By James Charlesworth ChatGPT's Problem With JSON Open up the ChatGPT UI and ask it for some JSON. Chances are you will get a response like you can see in the cover photo above: a JSON object presented to you in markdown format, with some text to eit...
freeCodeCamp — ChatGPT7 min readPrompt Engineering
Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights.
Lil'Log (Lilian Weng)20 min readHow to Build an Open-Domain Question Answering System?
[Updated on 2020-11-12: add an example on closed-book factual QA using OpenAI API (beta). A model that can answer any question with regard to factual knowledge can lead to many useful and practical applications, such as working as a chatbot or an AI assistant🤖.
Lil'Log (Lilian Weng)32 min read
Showing 529 of 529 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts