jasfi

Related: an intelligence cache for decision model data: https://cachev.dev

I built this for my own needs, and thought others might find it useful too.

I was building a trading indicator with Jev and wanted an intelligent cache to reduce the volume of usage-based API calls. That's when I came up with the idea for CacheV, it's built specifically for that use case, and works with any decision model.

A software factory: https://sfactory.dev

LLMs wouldn't work without learning on massive amounts of text, so using the entirety of human thought and existence is a very practical step. I wouldn't worry about the reselling part, because AI is a race towards the best price/performance. Open weights models are driving the price down a huge amount, making this tech more practical for everyone.

I'm looking for beta testers for Sfactory. Right now it's focused on quality AI writing. Please give it a try if this is of interest to you.

I wrote something similar, but as others have pointed out not having a formal language can be a hindrance.

I played it! Couldn't remember the name but it is the same game as linked to that I do remember.

I've read that you should take K2 if you take D3. You might want to research that. Also 500 IU of D3 is really low.

It's about the ability to combine ideas in novel ways, without breaking the rules in relevant frameworks. Sometimes the idea may even be to contradict existing theories where they are weak.

I wrote IntentCode, but it seems to have gone under the radar: https://github.com/jfilby/intentcode

I've built an AI compiler that has my take on this: https://github.com/jfilby/intentcode

I wrote something similar where you specify the intent in Markdown at the file level. That can also be done by an AI agent. Each intent file compiles to a source file.

It works, but needs improvement. Any feedback is welcome!

https://intentcode.dev

https://github.com/jfilby/intentcode

Hi HN,

I wrote IntentCode to let people write high-level specs in natural language, or directly in pseudo-code (Markdown with guidelines I call the IntentCode).

This is an AI compiler, the IntentCode files get compiled to source 1:1. The examples so far are quite basic (calc CLI app) but prove that the concept is sound.

You can also write extensions, which are mainly skills files for now.

I intend to keep progressing the compiler, so that larger and more complex examples can be implemented.

I wrote something similar: https://intentcode.dev

An AI compiler, releasing later today: https://intentcode.dev

I'm actually building this and believe I've overcome the most difficult aspects mentioned here. It will be released as Open Source next week. https://intentcode.dev

Benchmarks would be nice to help understand the performance implications.

Likely if they sponsor a ton of tokens.

I'm actually building this, will release it early next month. I've added a URL to watch to my profile (should be up later this week). It will be Open Source.

Try Lutein (20mg).

That's a role that would require AGI, we're not there yet.

Please add a 2nd page.

Nim hit the spot for a good low-level, fast language for me. The recommended GCs work well and it's easy to use.

Sorry to hear that. Given that it's genetic only something like Crispr could perhaps one day help.

Lutein may prevent or slow it. It's the best general eye supplement I've found too.

Thanks, it looks professionally done.

What are you using to put your videos together?

Easily solved, pairs of models, one which would rather say IDK, one which would rather guess. Most AI agents would want the IDK version.

I noticed this too, using it for https://kindred.fit.

That's why "make something people want" is such a core saying for startups.