• Causality of an LLM's emergent multilingual capabilities and how to fully harness this phenomenon for multilingual LLM performance
• Data attribution for LLMs: what data do we actually need to address the failure mode we are targeting?

currently pursuing ideas about how language models can be useful and valuable, which I currently define by possibly:

• accomplish better outcomes with less resources
• make something previously hard/impossible to accomplish possible

hypothesis #1: encoding domain expertise into an input-output interface which scales knowledge distribution orders of magnitude better

• if experts can encode their hard-earned intuition, they can scale thier expertise to users that no longer need to go through the same learning curve

• finetuned and preference optimisation Mistral 7B v0.1 base to answer questions on athletic training based on the PJF method a.k.a the moneyball of exercise science
• RAG-type system might be more suited for this use case

(WIP) hypothesis #2: powerful tool for thought: process complex information and generate useful insights at a higher throughput

• built Rivendell which summarises >50 page documents without missing critical information
• Next Step: integrating this into real world applications that create value for users
  • Promising use cases: patent analysis and writing, updating medical knowledge databases

(WIP) hypothesis #3: powerful tool for creativity: identify patterns that are tediuos and not immediately obvious

Gigit AI is a platform that helps WhatsApp Businesses scale personalised customer interactions with AI-generated messages.

We learnt that a subset of growing businesses that are operationally heavy drive their sales through WhatsApp, but there were insufficient tools built for them to scale. Their go-to solution was to scale their manpower linearly to their demands, which is why we built Gigit to solve this.

worked extensively on retrieval augmented generation (RAG) applications. Developed our own techniques to maximise the quality and reliability of our product, experimented with various interfaces for serving customers. happy to share what we learnt through the process!

I'll always cherish my time at Gigit. We served great customers and innovated intensely, which stretched me to my best.