AI/LLM Security Articles

back to AI/LLM Security

Training & Alignment

AI/LLM Security → Training & Alignment

1 weeks ago

Part 13 of the AI/LLM mastery series — how a model learns not just to answer, but to answer the way humans prefer. RLHF explained:…

#ai #Alignment #DPO #Fundamentals

AI/LLM Security

1 weeks ago

Part 12 of the AI/LLM mastery series — turning a knowledgeable base model into a helpful assistant by changing its behaviour, not …

#ai #Fine-Tuning #Fundamentals #Instruction Tuning

AI/LLM Security

1 weeks ago

Part 11 of the AI/LLM mastery series — the unglamorous machinery that decides model quality. How a raw web scrape (mostly junk) be…

#ai #Data Quality #Fundamentals #LLM

AI/LLM Security

1 weeks ago

Part 10 of the AI/LLM mastery series — the maths of "bigger, more data, more compute". The three levers (parameters, tok…

#ai #Chinchilla #Fundamentals #LLM

AI/LLM Security

1 weeks ago

Part 9 of the AI/LLM mastery series — how a randomly-initialised GPT becomes one that knows the world. Pretraining: the trillions …

#ai #Base Model #Fundamentals #LLM