· ai
2025: The Year in LLMs
'Cleaned Markdown
-
- · ai
2025: The Year in LLMs
Article URL: https://simonwillison.net/2025/Dec/31/the-year-in-llms/ Comments URL: https://news.ycombinator.com/item?id=46449643 Points: 56 Comments: 21...
- · ai
Welcome to 2025 Wrapped 🚀
Overview In 2025 we witnessed major launches in technology. AI became more powerful, while cyber‑risk also increased. The FBI recovered over 60 million stolen...
- · ai
Chunk Size as an Experimental Variable in RAG Systems
Understanding retrieval in RAG systems by experimenting with different chunk sizes The post Chunk Size as an Experimental Variable in RAG Systems appeared first...
- · ai
Apple may see the future of LLMs very differently than most: report
Apple has been subject to a lot of criticism over its AI strategy, especially after it delayed several powerful Siri upgrades earlier this year. But a new repor...
- · ai
When long conversations cause context drift and hidden errors
Why long threads feel consistent but secretly drift I kept a single chat open for a week while pairing with a model on a refactor. At first the suggestions mat...
- · ai
Building Your Career in AI: Real Talk from the Trenches
Inspired by insights from Andrew Ng and Lawrence Moroney's career‑advice talk > “Look, the AI space is absolutely wild right now. As someone who's been deep in...
- · ai
Implementing Vibe Proving with Reinforcement Learning
How to make LLMs reason with verifiable, step-by-step logic Part 2 The post Implementing Vibe Proving with Reinforcement Learning appeared first on Towards Data...
- · ai
Prompt Engineering From First Principles: The Mechanics They Don't Teach You part-1
'Prompt‑Engineering Series – Part 1 The Foundations – How LLMs Really Work
- · ai
So Long, GPT-5. Hello, Qwen
In the AI boom, chatbots and GPTs come and go quickly. Remember Llama? GPT-5 had a big year, but 2026 will be all about Qwen....
- · ai
Mixtral of Experts
Overview Mixtral 8x7B is a language model that distributes tasks across many tiny specialists, achieving both speed and intelligence. It employs a Sparse Mixtu...
- · ai
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Researchers built a very large language system called Gopher to see what happens when computers read lots and lots of writing. As the models grew in scale, they...