valstu

> However, skills are different from MCP. Skills has nothing to do with tool calling at all

Although skills require that you have certain tools available like basic file system operations so the model can read the skills files. Usually this is implemented as ephemeral "sandbox environment" where LLM have access to file system and can also execute python, run bash commands etc.

Nope, not yet. We have sticked with markdownish syntax so far.

We're doing something similar. We first chunk the documents based on h1,h2,h3 headings. Then we add headers in the beginning of the chunk as a context. As an imagenary example, instead of one chunk being:

  The usual dose for adults is one or two 200mg tablets or 
  capsules 3 times a day.

It is now something like:

  # Fever
  ## Treatment
  ---
  The usual dose for adults is one or two 200mg tablets or 
  capsules 3 times a day.

This seems to work pretty well, and doesn't require any LLMs when indexing documents.

(Edited formatting)

So regex version still beats the LLM solution. There's also the risk of hallucinations. I wonder if they tried to make SML which would rewrite or update the existing regex solution instead of generating the whole content again? This would mean less output tokens, faster inference and output wouldn't contain hallucinations. Although, not sure if small language models are capabable to write regex

I just recently found out that there is Deno kernel for Jupyter notebook

https://blog.jupyter.org/bringing-modern-javascript-to-the-j...

Chroma used DuckDB at some point, might not be the case anymore though

We use the term "pre-googling" for this sort of "information retrieval". You might have some concept in your head and you want to know the exact term for it, once you get the term you're looking for from LLM you'll move to Google and search the "facts".

This might be a weird example for native english speakers but recently I just couldn't remember the term for graph where you're allowed to move in one direction and cannot do loops. LLM gave me the answer (directed acyclic graph or DAG)right away. Once I got the term I was looking for I moved on to Google search.

Same "pre-googling" works if you don't know if some concept exits.

I assume you need to split the data to suitable sized database rows matching your model max length? Or does it do some chunking magic automatically?

I wonder how this compares to https://vlcn.io?

Doesn't same question apply to any content you're about read? How can you know that the blog post/article writer didn't "hallucinate"?

This is 3 years old but still pretty well done explanation of the case MH370 https://www.youtube.com/watch?v=kd2KEHvK-q8

Well, I asked GPT-3 to make this longer:

One of the surest ways to come up with new ideas is to pay attention to what doesn't fit in. We're used to seeing things in a certain way, and often times it's the things that don't quite fit into our preconceived notions that can provide the best insights. The most obvious place to look for these anomalies is at the frontiers of knowledge.

Knowledge grows like a fractal; from a distance its edges may appear smooth, but when you get closer you begin to see the jagged gaps and spaces. These gaps can be surprisingly obvious; it can seem strange that no one has thought to ask a certain question or investigate a certain problem. When you explore them, you can often discover entirely new areas of knowledge that have been previously untouched.

That's why it's useful to investigate these gaps in knowledge. It may feel uncomfortable at first; we don't always like to challenge our preconceptions and explore things beyond our comfort zone. But often times this can be the source of some of our best ideas.

You don't even have to look far for these anomalies; they can be found in everyday life. Much of stand-up comedy is based on this, by finding the oddities and quirks about our daily lives that we normally take for granted.

So don't be afraid to take a closer look at what seems strange or missing or broken. It could lead you to unexpected discovery and perhaps even uncover some of your best ideas. This may be challenging and uncomfortable, but it's often worth it.

Are there any ”api from postgres db” projects that are written in Node.js?

So this where Daft Punk got the inspiration for their helmets

"Tell me you're developer without telling me"

Could I build webassembly.studio like page with Runno (compile C code to webassembly)?