841
842
MCP: An (Accidentally) Universal Plugin System
Or: The Day My Toaster Started Taking Phone Calls
843
I think I'm done thinking about GenAI for now
The conversation isn’t over, but I don’t think I have much to add to it.
844
WASM Agents: AI agents running in the browser
One of the main barriers to a wider adoption of open-source agents is the dependency on extra tools and frameworks that need to be installed before the agents can be run. In this post, we show how to write agents as HTML files, which can just be opened and run in a browser.
845
Normalizing Flows Are Capable Generative Models
Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density…
846
Reverse engineering Codex CLI to get GPT-5-Codex-Mini to draw me a pelican
OpenAI partially released a new model yesterday called GPT-5-Codex-Mini, which they describe as "a more compact and cost-efficient version of GPT-5-Codex". It’s currently only available via their Codex CLI tool …
847
MCP explained without hype or fluff
Model Context Protocol, like most protocols, solves the M ⨯ N integration problem by turning it into an M + N integration problem.
848
Our new SAM audio model transforms audio editing
We're introducing SAM Audio, a state-of-the-art AI model that enables you to segment sound.
849
Using LLMs and Cursor to finish side projects
Struggling to finish side projects due to limited time? In my latest blog post, I share how I improved my productivity using AI tools like LLMs and Cursor IDE. Learn to refine specs, bootstrap code, and iterate effectively to rapidly build and deploy your projects—even with a busy schedule.
850
Batch Mode in the Gemini API: Process More for Less
Discover how Batch Mode in Gemini API allows developers to submit large jobs, offload processing, and get results in 24 hours, offering simplicity, convenience, and cost-savings.
851
Diffusion models explained simply
Transformer-based large language models are relatively easy to understand. You break language down into a finite set of “tokens” (words or sub-word components…
852
Building a Mac app with Claude code
How I built Context—a native macOS SwiftUI app for debugging MCP servers—almost entirely with Claude Code, and what I learned about building with AI coding agents.
853
Sycophancy is the first LLM "dark pattern"
People have been making fun of OpenAI models for being overly sycophantic for months now. I even wrote a post advising users to pretend that their work was…
854
Should LLMs just treat text content as an image?
Several days ago, DeepSeek released a new OCR paper. OCR, or “optical character recognition”, is the process of converting an image of text — say, a scanned…
855
When a stadium adds AI to everything, it's worse experience for everyone
I just got back from a 24hr trip to Los Angeles to catch my favorite Portland Thorns team, watching them clinch their playoff spot in a match at BMO stadium in downtown Los Angeles. In May of 2024, I did the same trip to catch a match on Mother's
856
857
When Jorge Luis Borges met one of the founders of AI
One reason I became a historian is the joy of encountering moments in the past that are foreign, yet also oddly familiar.
858
Implementing LLaMA3 in 100 Lines of Pure Jax
Hi, welcome to my website! This is where I share my thoughts on things that interest me, mostly tech, philosophy, history, and math.
859
GPT-4.5: "Not a frontier model"?
OpenAI's latest model raises more questions than answers, but no, the AI bubble isn't popping quite yet.
860
Email immutability matters more in a world with AI
Email immutability matters even more in a world of AI. Here is how we enable your use of your data, in line with our values.
861
Finding thousands of exposed Ollama instances using Shodan
We uncovered 1,100+ exposed Ollama LLM servers—20% with open models—revealing critical security gaps and the need for better LLM threat monitoring.
862
Building a Knowledge System That Enhances Rather Than Replaces Thought
Preserving and augmenting human insight in an age of automated knowledge with Zettelgarden
863
How much Anthropic and Cursor spend on Amazon Web Services
So, I originally planned for this to be on my premium newsletter, but decided it was better to publish on my free one so that you could all enjoy it. If you liked it, please consider subscribing to support my work. Here’s $10 off the first year of annual.
864
O3 Turns Pro
You can now have o3 throw vastly more compute at a given problem.
865
AI, Heidegger, and Evangelion
Our brains, evolved for tribal politics and campfire stories, are ill-equipped for the moral ambiguity of a system with no soul to save or damn.
866
Pose Animator – An open source tool to bring SVG characters to life (2020)
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.
867
NSF and Nvidia award Ai2 $152M to support building an open AI ecosystem
Ai2 has been awarded a combined $152 million from the U.S. National Science Foundation (NSF) and NVIDIA as part of a jointly funded project to advance our research and develop truly open AI models and solutions that will accelerate scientific discovery.
868
After the AI boom: what might we be left with?
Some argue that even if the current AI boom leads to an overbuild, it might not be a bad thing - just as the dotcom bubble left behind the internet infrastructure that powered later decades of growth. It’s a tempting comparison, but the parallels only go so far. The dotcom era’s overbuild crea
869
Omnilingual ASR: Advancing automatic speech recognition for 1600 languages
We’re introducing Meta Omnilingual Automatic Speech Recognition, a suite of models providing automatic speech recognition capabilities for over 1,600 languages.
870
I've been loving Claude Code on the web
It’s very much a “v1” product. You type a prompt to start a new thread, it launches a little container for your agent to work in, and you can keep talking to it. It produces a branch, which you can open a PR for (that’s the only way to see a diff of the changes Claude Code made, for now). Or if you want to keep…