571
Optimizing Datalog for the GPU
Datalog primer and a neat data structure
572
What makes 5% of AI agents work in production?
Beyond the Prompt: Notes from the Context Frontier
573
Asking Gemini 3 to generate Brainfuck code results in an infinite loop
Asking Gemini 3 to generate Brainf*ck code results in an infinite loop, akin amost to a DDoS attack:
574
"Wait, not like that": Free and open access in the age of generative AI
The real threat isn’t AI using open knowledge — it’s AI companies killing the projects that make knowledge free
575
Hacking Diffusion into Qwen3 for the Arc Challenge
A deep dive into ongoing efforts adapting language models for diffusion-based ARC solving.
576
The Claude Code Framework Wars
How developers are experimenting with structure, orchestration, and standards to get more out of AI coding.
577
578
GPT might be an information virus (2023)
Obligatory: the views and opinions expressed in this post are my own and do not represent the views and opinions of my employer. In light of all the hype going around about ChatGPT, I wanted to offer my “hot take” on what the next 2-5 years
579
OpenAI is a systemic risk to the tech industry
Before we go any further: I hate to ask you to do this, but I need your help — I'm up for this year's Webbys for the best business podcast award. I know it's a pain in the ass, but can you sign up and vote for Better
580
The Sky's the limit: AI automation on Mac
I’ve been sitting on this draft for a few days now, partly because I thought it would turn down the bitterness, and partly because I kept asking myself ...
581
How outdated information hides in LLM token generation probabilities
Random tech notes
582
The vibe coder's career path is doomed
Let me get one thing out of the way immediately: LLMs are helpful. This isn't about whether LLMs can write code. They can. It's about why vibe coding might be the worst career investment you'll make.
583
584
AI coding and the peanut butter and jelly problem
Why clear communication—not clever prompts—is your real AI superpower
585
Baby Steps into Genetic Programming
While my final ranking in the Google AI Contest was disappointing ( 280th ), it was a very educational experience and was totally offset by Gábor Melis' dominating win using Common Lisp as well.
586
Optimizing Tool Selection for LLM Workflows with Differentiable Programming
How local, learnable routers can reduce token overhead, lower costs, and bring structure back to agentic workflows.
587
Adventures in Symbolic Algebra with Model Context Protocol
Personal blog of Stephen Diehl - Software engineer writing about technology, programming, and the future
588
Towards the Cutest Neural Network
I recently needed to use a microcontroller to estimate the pose (translation and orientation) of an object using readings from six different sensors. Since the readings were non-linear and coupled with each other, an explicit analytical solution was out of the question.
589
The AI wildfire is coming. it's going to be painful and healthy
AI won’t crash—it will burn. Like every tech cycle, the fire will clear the brush, redistribute talent, and leave infrastructure to power what comes next. The question is: what kind of plant are you?
590
Vibe Coding and the Future of Software Engineering
Vibe coding (or vibeware) is making rounds on X now. To the best of my knowledge Andrej Karpathy started the “meme” in this X entry . I find it well written and hilarious and it seems to have taken off.
591
AMD YOLO
AMD is sending us the two MI300X boxes we asked for. They are in the mail.
592
The inefficiency of RL, and implications for RLVR progress
And implications for RLVR progress
593
Evaluating LLMs for my personal use case
My life is not a math Olympiad
594
ML on Apple ][+
Success! There is machine learning happening on my Apple ][+.
595
How Cursor (AI IDE) Works
Turning LLMs into coding experts and how to take advantage of them.
596
Agentic pelican on a bicycle
The agentic loop—generate, assess, improve—seems like a natural fit for iterating on pelicans on bicycles.
597
Whistleblower: Huawei cloned Qwen and DeepSeek models, claimed as own
A now-deleted report by HonestAGI on GitHub showed a high number of similarities between Huawei’s Pangu and Qwen 2.5.
598
The Generative Burrito Test
A critical benchmark for image generation models: A partially eaten burrito with cheese, sour cream, guacamole, lettuce, salsa, pinto beans, and chicken.
599
Revisiting Minsky's Society of Mind in 2025
AI Agents, Modularity, and Alignment
600
Evaluating LLMs playing text adventures
When we first set up the llm such that it could play text adventures , we noted that none of the models we tried to use with it were any good at it. We dreamed of a way to compare them, but all I could think of was setting a goal far into the game and seeing how long it takes them to get there. I just realised there’s…