Mistral OCR
New closed-source specialist OCR model by Mistral - you can feed it images or a PDF and it produces Markdown with optional embedded images. It's available [via their API](https://docs.mistral.ai/api/#tag/ocr), or …
llms
Mistral OCR | Mistral AI
Introducing the world’s best document understanding API.
Mistral’s new OCR API turns any PDF document into an AI-ready Markdown file
Large language models work particularly well with raw text. Companies that want to create their own AI workflow know that it has become extremely
llm-mistral 0.11
I added [schema support](https://simonwillison.net/2025/Feb/28/llm-schemas/) to this plugin which adds support for the [Mistral API](https://docs.mistral.ai/api/) to LLM. Release notes: - Support for LLM [schemas](https://llm.datasette.io/en/stable/schemas.html)…
llm-ollama 0.9.0
This release of the `llm-ollama` plugin adds support for [schemas](https://simonwillison.net/2025/Feb/28/llm-schemas/), thanks to a [PR by Adam Compton](https://github.com/taketwo/llm-ollama/pull/36). Ollama provides very robust support for this pattern thanks to their…
Claude 3.7 Sonnet and Claude Code
Today, we’re announcing Claude 3.7 Sonnet, our most intelligent model to date and the first hybrid reasoning model generally available on the market.
The Deep Research problem — Benedict Evans
OpenAI’s Deep Research is built for me, and I can’t use it. It’s another amazing demo, until it breaks. But it breaks in really interesting ways.
5 Principles for Writing Effective Prompts (2025 Update)
Solid techniques to get really good results from any LLM
Greg Brockman shared this template for prompting
OpenAI's president Greg Brockman recently shared this cool template for prompting their reasoning models o1/o3. Turns out, this is great for ANY reasoning… | 32 comments on LinkedIn
LLM Leaderboard
Comparison and ranking the performance of over 30 AI models (LLMs) across key metrics including quality, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others.
BERT
BERT is an open source machine learning framework for natural language processing (NLP) that helps computers understand ambiguous language by using context
Here Are My Go-To AI Tools
I share my preferences for LLMs, image models, AI video, AI music, AI-powered research, and more. These are the AI tools I regularly use or recommend to others.
A Step-by-Step Guide to Setting Up a Custom BPE Tokenizer with Tiktoken for Advanced NLP Applications in Python
We Were Wrong About GPUs
Do my tears surprise you? Strong CEOs also cry.
sqlite-s3vfs
Neat open source project on the GitHub organisation for the UK government's Department for Business and Trade: a "Python virtual filesystem for SQLite to read from and write to S3." …
Using pip to install a Large Language Model that’s under 100MB
I just released llm-smollm2, a new plugin for LLM that bundles a quantized copy of the SmolLM2-135M-Instruct LLM inside of the Python package. This means you can now pip install …
Understanding Reasoning LLMs
In this article, I will describe the four main approaches to building reasoning models, or how we can enhance LLMs with reasoning capabilities. I hope this p...
My approach to running a link blog
I started running a basic link blog on this domain back in November 2003—publishing links (which I called “blogmarks”) with a title, URL, short snippet of commentary and a “via” …
5 AI Agent Frameworks Compared - KDnuggets
Check out this comparison of 5 AI frameworks to determine which you should choose.
(WIP) A Little Bit of Reinforcement Learning from Human Feedback
The Reinforcement Learning from Human Feedback Book
Creating an AI Agent-Based System with LangGraph: Adding Persistence and Streaming (Step by Step Guide)
In our previous tutorial, we built an AI agent capable of answering queries by surfing the web. However, when building agents for longer-running tasks, two critical concepts come into play: persistence and streaming. Persistence allows you to save the state of an agent at any…
aidanmclaughlin/AidanBench: Aidan Bench attempts to measure in LLMs.
Aidan Bench attempts to measure in LLMs. - aidanmclaughlin/AidanBench
OpenAI o3-mini, now available in LLM
o3-mini is out today. As with other o-series models it’s a slightly difficult one to evaluate—we now need to decide if a prompt is best run using GPT-4o, o1, o3-mini …
Multi-Head Latent Attention and Other KV Cache Tricks
How a Key-Value (KV) cache reduces Transformer inference time by trading memory for computation
Qwen AI Introduces Qwen2.5-Max: A large MoE LLM Pretrained on Massive Data and Post-Trained with Curated SFT and RLHF Recipes
The field of artificial intelligence is evolving rapidly, with increasing efforts to develop more capable and efficient language models. However, scaling these models comes with challenges, particularly regarding computational resources and the complexity of training. The…
Alibaba releases AI model it says surpasses DeepSeek
The unusual timing of the Qwen 2.5-Max's release points to the pressure DeepSeek's meteoric rise in the past three weeks has placed on overseas rivals and domestic competition.
On MLA
The Illustrated DeepSeek-R1
A recipe for reasoning LLMs
DeepSeek-R1 vs. OpenAI’s o1: A New Step in Open Source and Proprietary Models
AI has entered an era of the rise of competitive and groundbreaking large language models and multimodal models. The development has two sides, one with open source and the other being propriety models. DeepSeek-R1, an open-source AI model developed by DeepSeek-AI, a Chinese…
ChatGPT Operator system prompt
Johann Rehberger snagged a copy of the [ChatGPT Operator](https://simonwillison.net/2025/Jan/23/introducing-operator/) system prompt. As usual, the system prompt doubles as better written documentation than any of the official sources. It asks users …
AI hallucinations can’t be stopped — but these techniques can limit their damage
Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.
Noteworthy LLM Research Papers of 2024
This article covers 12 influential AI research papers of 2024, ranging from mixture-of-experts models to new LLM scaling laws for precision..
LLM 0.20
New release of my [LLM](https://llm.datasette.io/) CLI tool and Python library. A bunch of accumulated fixes and features since the start of December, most notably: - Support for OpenAI's [o1 model](https://platform.openai.com/docs/models#o1) …
How Chinese A.I. Start-Up DeepSeek Is Competing With OpenAI and Google
The company built a cheaper, competitive chatbot with fewer high-end computer chips than U.S. behemoths like Google and OpenAI, showing the limits of chip export control.
Inbox | Substack
DeepSeek-R1 and exploring DeepSeek-R1-Distill-Llama-8B
DeepSeek are the Chinese AI lab who dropped the best currently available open weights LLM on Christmas day, DeepSeek v3. That model was trained in part using their unreleased R1 …
Microsoft Presents a Comprehensive Framework for Securing Generative AI Systems Using Lessons from Red Teaming 100 Generative AI Products
The rapid advancement and widespread adoption of generative AI systems across various domains have increased the critical importance of AI red teaming for evaluating technology safety and security. While AI red teaming aims to evaluate end-to-end systems by simulating real-world…
Lessons From Red Teaming 100 Generative AI Products
New paper from Microsoft describing their top eight lessons learned red teaming (deliberately seeking security vulnerabilities in) 100 different generative AI models and products over the past few years. …
Implementing A Byte Pair Encoding (BPE) Tokenizer From Scratch
This is a standalone notebook implementing the popular byte pair encoding (BPE) tokenization algorithm, which is used in models like GPT-2 to GPT-4, Llama 3,...
This Rumor About GPT-5 Changes Everything
Let’s start the year on an exciting note
The 2025 AI Engineering Reading List
We picked 50 paper/models/blogs across 10 fields in AI Eng: LLMs, Benchmarks, Prompting, RAG, Agents, CodeGen, Vision, Voice, Diffusion, Finetuning. If you're starting from scratch, start here.
Note: gist: https://gist.github.com/bjpcjp/117ecf144c062c3c933f2690e7ece5c2
Agents
Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines the field of AI research as “the study and design of rational agents.”
Note: I have expanded the previous summaries of each section and paragraph from Chip Huyen's article "Agents," published on January 7, 2025, by including links to the resources cited within the article. **Agent Overview** 1. The term "agent" has been used in various engineering contexts, including software agents, intelligent agents, user agents, conversational agents, and reinforcement learning…
100 Must-Read Generative AI Papers from 2024
A comprehensive list of some of the most impactful generative papers from last year
7 Next-Generation Prompt Engineering Techniques - MachineLearningMastery.com
[caption align=
How to use NotebookLM for personalized knowledge synthesis
Two powerful workflows that unlock everything else. Intro: Golden Age of AI Tools and AI agent frameworks begins in 2025.
An Opinionated Evals Reading List — Apollo Research
A long reading list of evals papers with recommendations and comments by the evals team.
Things we learned out about LLMs in 2024
A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past …
How to Build a Graph RAG App
Using knowledge graphs and AI to retrieve, filter, and summarize medical journal articles
Note: requires weaviate account 25 per month lowest tier
ChatGPT search vs. Google: A deep dive analysis of 62 queries
A detailed analysis of ChatGPT search and Google's performance across 62 queries, with scoring metrics and practical examples.
Each response was meticulously fact-checked and evaluated for alignment with potential user intents.
two-thirds of which were informational
Gemini 2.0 Flash "Thinking Mode"
Plus building Python tools with a one-shot prompt using uv run and Claude Projects