I prefer faster, dumber models because I provide the intelligence myself and I use them only for things that can be verified pretty easily; they do research (with sources) for me, do certain types of code analysis and code search, boilerplate generation, etc., so a fast model is really key.
I don't have any desire (or think it's a good use of LLMs) to one-shot features because even SotA models are incredibly bad at this. I'm optimizing for what they actually seem to be able to do reliably and pretty well, and I want those things to be done fast so I can get on with things.
Generally thinking tokens are the ones which are verbose. So the speed helps with reducing time for thinking tokens generations and you get your actual output code very fast.
Micro.mu looks interesting, your description of daily digital habits made me think it was a productivity app, when it really is more of a dashboard for different channels of content on the internet (social, video, chat, etc.) what was your original vision? I am curios. Also I really like the design, its so clean, Ive never seen anything quite like it and yet it seems like such a good aesthetic that should have been obvious. kuddos.
Originally I felt there should be an alternative to Google and Facebook. It felt like our lives were being ruled by tech giants even ten years ago..and then all the advertising and algorithms really messed with us. I personally wanted an alternative way to use the web. So it's based around what I'd use on a daily basis. And then the idea of being able to extend it with a native app builder. The big stuff I continue to build with Go but ad-hoc things I can knock out with some JS in the app itself.
www.propelcode.app - cursor on my phone.
www.propelagent.app - voice agent for my home health care agency, but it also tells bed time stories to me and my daughter a few times a month.
I also built a new web framework we use internally which is amazing. We might open source it soon. It has a postman clone that has a bunch of features I wanted. It really is the case that we can just build tools any time we want.
I agree. I feel like sonnet 4.6 is sufficient for almost everything. Beyond that level it feels like the orchestration is more important.
That being said the models still surprise me with a broad range of hallucinations, lack of epistemology or common sense or inability to follow instructions on a daily basis.
Today it was trying to get opus 4.8 to just follow a simple architectural pattern for controllers in a rails app. It was pulling teeth out of a shark.
You absolutely need to get inflation adjusted bonds. Otherwise you’ll get wiped out. I am in the krugman, stiglitz monetary camp; so not prone to constant fear of hyperinflation but what the government is doing makes inflation certain and the only way out a fairly painful recession either of will be hard on equity and bonds.
The market of a good leader is a lack of chaos. We are seeing the effects of a chaotic mind untethered from an accurate view of reality. Buckle up
This feels like the notorious Dropbox objections when it launched. Just because it's easy to you doesn't mean it's easy for everyone. I can see this being really useful for my product which is cursor on my phone/computer/and browser. I built an IDE with a Linux container so I could have a real dev environment and file system on my iPhone. It let's me code at the beach with my kids (plan and epic have the AI do a massive pull request while I am having fun for 30 mins with the family. Spend 5 minutes giving the code a look which often finds some large concerns that warrant a new prompt etc). The containers were actually a huge pain to set up and I am still not satisfied with my implementation.
I'll definitely check this out. This project is actually perfect for several projects i am working on.
There are a category of super apps that haven’t really been possible before because they threshold of utility required too many features to realistically build. Think SAP or EPIC or an operating engine to run an enterprise. But now they are possible and building all the features will give a business something they have never had.
But you still need to talk to customers to translate their domain expertise into prompts into code.
Cool project. I don’t think people will get the mobile version until they need it but when they do it’s a mind bending, life changing realization. I built my own IDE to have it on my phone because I have small kids and it is truly life changing. I get to spend way more time with my kids while still getting work done.
If you’re open to collaborating I’d be happy to share what I’ve learned an see if we can share resources or lessons.
reply