May 2026
Intermediate to advanced
340 pages
8h 45m
English
Content preview from Large Language Models: The Hard PartsBecome an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Index
A
- Abstraction and Reasoning Corpus (ARC) Prize, ARC-AGI and the Prize
- accuracy, Performance Requirements, Methodologies for Evaluation, Coding BLEU and ROUGE, Evaluating Evaluators, Conclusion
- testing for LLMBA outputs, Misinformation Prevention
- adversarial red-teaming attacks (HarmBench), HarmBench
- adversarial testing, LLM Safety Considerations, Red Teaming
- AGI (artificial general intelligence), ARC-AGI and the Prize
- AI (artificial intelligence), general safety risks, General AI Safety Risks
- AI center of excellence (COE), Centralized Framework
- AI frameworks (organizational) (see organizational AI frameworks)
- AI Officer (chief), Centralized Framework
- AI safety levels (ASLs), Anthropic
- AIS (MLCommons AI Safety Working Group), MLCommons AI Safety Benchmark
- Alibaba Cloud Qwen2.5-0.5B model, Outlines
- Alibaba’s Qwen2.5 licenses, Licensing
- alignment of LLMs (see policy alignment of LLMs)
- all-MiniLM-L6-v2 model, Vector Embeddings
- use by ChromaDB, Vector databases
- AlpacaEval Leaderboard, A Brief Tour of LLM Benchmarks
- anonymization of data, Privacy Protection
- Anthropic
- Constitutional AI, for enhancement of LLM safety, Constitutional AI-Enhancing transparency and scalability
- contextual retrieval, Generating long-form content
- safety guidance for LLMs
- Apache 2.0 licenses, Licensing
- API servers for local models, llama-server
- ARC (Abstraction and Reasoning Corpus) Prize, ARC-AGI and the Prize
- ARC-AGI ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.