Large-language models (LLMs) are great generalists, but modifications are required for optimisation or specialist tasks. The easiest choice is...

Large-language models (LLMs) are great generalists, but modifications are required for optimisation or specialist tasks. The easiest choice is Retrieval Augmented Generation (RAG) with in-context, which has become easier with OpenAI's custom GPTs. The hardest and most unattainable option is creating a specialist LLM from scratch. But you can achieve much of it by simply adjusting an existing LLM like ChatGPT, a process called fine-tuning. You can do that with open-source or commercial models...

How to Build Training Datasets and Fine-tune ChatGPT

Today, I received access to the new custom GPT feature on ChatGPT, and it appears to do what Sam Altman demonstrated. The implications are...

GPTs, mini RAGs, Omniscience, Data Silos and Monopoly (image: DALL·E 3)

Today, I received access to the new custom GPT feature on ChatGPT, and it appears to do what Sam Altman demonstrated. The implications are far-reaching, beyond the death of the RAG business model. How can OpenAI achieve and capitalise on Omniscience in a world of organisational data silos and increasingly defensive content creators and legislators?

OpenAI Custom GPTs: A Content Backdoor to Omniscience?

OpenAI's DevDay announcement yesterday addresses issues I wrote about in the infeasibility of RAG after building Llamar.ai this summer. Did I get...

Open AI is killing RAG (image: DALL·E 3)

OpenAI's DevDay announcement yesterday addresses issues I wrote about in the infeasibility of RAG after building Llamar.ai this summer. Did I get it wrong? Working through the details will take some time, but interesting immediate observations are apparent.

Is OpenAI killing Retrieval Augmented Generation?

Over four months, I created a working retrieval-augmented generation (RAG) product prototype for a sizeable potential customer using a...

Llama looking through a fence

Over four months, I created a working retrieval-augmented generation (RAG) product prototype for a sizeable potential customer using a Large-Language Model (LLM). It became a ChatGPT-like expert agent with deep, up-to-date domain knowledge and conversational skills. But I am shutting it down instead of rolling it out. Here is why, how I got there and what it means for the future.

Llamar.ai: A deep dive into the (in)feasibility of RAG with LLMs

Building retrieval-augmented generation, custom GPT and grounded AI products.

RAG and AI Applications

Articles

How to Build Training Datasets and Fine-tune ChatGPT

OpenAI Custom GPTs: A Content Backdoor to Omniscience?

Is OpenAI killing Retrieval Augmented Generation?

Llamar.ai: A deep dive into the (in)feasibility of RAG with LLMs