Category: AI

Overall, I’m still very happy with gpt-5.6-sol. My experiment to lower effort level to “medium” for most of my projects is going well. Doshmodo, hlsync, discovery engine and pluckso are all using the lowered level now. Million minds AI, on the other hand, I raised to “xhigh” and it really made a difference there. It…

Everyone is excited they can run large models on their home computers, and here I’m wondering, can we run frontier models more cheaply in the cloud without requiring specialty GPU hardware that is very hard to secure even if you have the money? https://arxiv.org/abs/2608.16157 https://github.com/FlashML-org/FreeToken

I seem to be doing very well with codex and perhaps it is my agents.md files. They are customized per project but here is the main gist: – Push back when what the user is saying is wrong or doesn’t match your understanding.– Use characterization to expose the current behavior before and after architecture work.…

There are many levels to engineering; some are in the weeds, handling the nits and grits, while others are guiding the vision and architecture from the hills. Some people are still stuck thinking unless they are in the belly of the beast, they are not engineering. They couldn’t be more wrong. AI did not change…

One area that needs a closer look if we are to achieve AGI is the ability to extract concepts from language and have a clean separation between what is learned and how to put it into words. Yes we already have some of that today, but it’s very nascent and crude relative to what humans…

I said @BenjDicken studying database papers was very inspirational but I never did anything about it last year. So let me get started.. Today’s paper is “Solving A Million-Step LLM Task With Zero Errors” Takeaways: * Break the task into many many (deterministic) micro-tasks * Run each task 2+ times to implement voting, aka ambiguity…