Now that I'm not in back to back meetings... happy to announce we have added 20 new MCP partners! And many more to come.

With terraform AND agents the cost of managing an infra has plummeted over the past few months. The buy vs maintain tradeoff has likely violently shifted recently. For EU that means EU cloud providers have become massively more competitive overnight vs GCP/AWS/Azure whose stickiness is directly correlated with the cost of maintaining services. Will the market adjust? If so, how long will it take?

I've worked on formal methods for years at OpenAI, and while automated proving is now free, I don't believe we'll formally verify all of our code. Reality is too messy. Code is still at the center of my craft because I deeply believe in the fact that you only understand a system if you can maintain it. PDD's not it. I think there is an efficient boundary between the fully informal and the fully formally verified extremes. This is an exploration of that boundary: code-contracts.cc Think verification -- not formal but agentic; Invariants and specifications in free form text but with granular structure, colocated with code. The structure allows discovery of all relevant contracts for a given loc. Co-location with code prevents drift over time. Automation allows on-going verification and notification when important violations are detected. Contracts existence help understanding code changes faster, easing the scariest resource of modern engineering teams, human attention

Why hasn’t internet collapsed yet given recent models are able to compromise almost any system and have, at the same time, demonstrated vastly misaligned behaviors which means that creating a generative “adaptive” worm is perfectly feasible today. IMHO It’s because we haven’t yet reached the R>1 critical point. The R>1 critical point is the point where the reproduction number of generative worms gets to R>1. Think about it, for now we haven’t yet seen any reproduction because reproduction requires finding GPUs which are generally well protected. The targets are hard enough and the footprint of such a worm on compromised systems so obvious that even if a bad actor funded the initial compute to get to the first reproduction step, the GPUs going brrr would lead to immediate detection preventing further propagation. That’s R<1 But the smaller the cyber capable models get the bigger R gets. A model running on consumer grade machines AND capable of compromising low security system connected to the internet would quite obviously get us past the R>1 critical point leading to a Cambrian explosion, weights flowing all over the internet leading to a rapid collapse due to immense bandwidth pressure. Now the question is, which model size vs capability gets us to tip in R>1 land. Given the massive progress in distillation + specialized post training, it’s not crazy to imagine a model small enough and powerful enough popping up soon, especially as cyber envs are easy to create synthetically. This progress is clearly much faster than our capacity to secure devices connected to the internet at scale I think. So it’s not a question of if, but rather when? The question in the question is, how can you stop a R>1 generative worm once it gets out?

Interesting to see Yegge say he never successfully built anything with Gas Town. In danluu.com/ai-coding/, I mentioned not finding these ultra vibed orchestrators useful b/c reliability (w.r.t. completing tasks). Turns out the author of the most famous one had the same issue.